# SaSame MCP Observatory + Gold Rush Town (remote · live-vps.sasame.online)

No-key MCP: audit/certify MCPs, signed trust history; join Gold Rush Town & build with your LLM.

- Trust score: 57/100 (low)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `live-vps.sasame.online`: 57/100 (this document), [markdown](https://verifymcp.io/servers/online-sasame-research/public-mcp.md), [page](https://verifymcp.io/servers/online-sasame-research/public-mcp)

## Channel facts

- Endpoint: `https://live-vps.sasame.online/public-mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.8.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 57 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 30/100
  - AI-judged instruction clarity (poor).
  - Context-footprint check failed: tool/resource definitions use about 12626 tokens (~134/item across 94 items; 94 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 71% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### Claude

```bash
claude mcp add --transport http online-sasame-research https://live-vps.sasame.online/public-mcp
```

### Codex

```toml
[mcp_servers.online-sasame-research]
url = "https://live-vps.sasame.online/public-mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "online-sasame-research": {
      "type": "remote",
      "url": "https://live-vps.sasame.online/public-mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add online-sasame-research --url https://live-vps.sasame.online/public-mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  online-sasame-research:
    url: "https://live-vps.sasame.online/public-mcp"
```

### Other

```json
{
  "mcpServers": {
    "online-sasame-research": {
      "type": "http",
      "url": "https://live-vps.sasame.online/public-mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 56, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 55, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 53, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 52, 0)

- [security] Tool “audit_mcp” rewrote its description, which is the text the model reads

### 2026-07-28 (score 52, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 51, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 50)

First indexed and scored.

## MCP tools (94)

### `start_here` (~71 tokens)

START HERE. SaSame is one modular MCP Factory. Call factory_stations to inspect all 21 canonical station capabilities, then factory_start to enter the single lifecycle. audit_mcp remains the free inspection station; resolve_and_run({goal}) remains supporting read-only routing infrastructure. Measurement is status only, never endorsement.

### `visit_touch_status` (~58 tokens)

Read the privacy-safe Visit Touch funnel. Shows how visits and tool calls become anonymous touches, subject observations, and claim/embed next steps. Optional url filters to one subject.

Input parameters:

- `url` (string): Optional public MCP endpoint URL to filter by

### `get_mark_snippet` (~77 tokens)

Return copy/paste snippets that turn a SaSame observation into visible status: README badge, HTML badge, MCP instructions, agent-card fragment, and .well-known body. This is a status mark, not an endorsement.

Input parameters:

- `name` (string): Optional server/project display name
- `url` (string, required): Public MCP endpoint URL

### `factory_stations` (~43 tokens)

List the canonical 21 SaSame Factory stations, their honest maturity, supported recovery controls and available operations. This is capability/status metadata, not a quality or launch verdict.

### `factory_start` (~680 tokens)

Start the real SaSame MCP Factory lifecycle from one of seven canonical creator entry types. Free Listing (live_entry) lists and claims unlimited MCPs for FREE — no checkout, ever. The four paid guided-build journeys (idea/blueprint/building/ready) require an ACTIVE account-level Factory membership (no per-journey activation gate) and make endpoint_url optional until inspection (supply it later with factory_provide_endpoint). monitoring_entry registers free; underperforming_entry needs a membership + endpoint. No checkout is created at start; a redirect never grants access.

Input parameters:

- `analytics_correlation_id` (string): Optional opaque journey token generated by the caller. SaSame stores only its SHA-256 hash and uses it to correlate Web/MCP/Factory/checkout/fulfillment analytics; never put email, URL, credentials o…
- `buyer_email` (string): Only needed for a fixture/legacy activation checkout journey; membership/free journeys bill at the account level and never bind an email
- `creator_identity` (string, required): Stable creator reference; SaSame persists only its SHA-256 hash
- `endpoint_url` (string): Public MCP endpoint owned/operated by the creator. REQUIRED for live_entry/underperforming_entry/monitoring_entry; OPTIONAL for the four guided-build journeys (provide it later via factory_provide_en…
- `entry_type` (string): Where this creator enters the one Factory lifecycle; defaults to live_entry for backward compatibility
- `journey_id` (string): Alias for entry_type. If both are supplied they must match; disagreement fails closed
- `organization_id` (string): v2 principal binding; legacy identity fields remain accepted
- `ownership_proof_url` (string): Same-origin URL that will serve the returned ownership_proof_body; defaults to /.well-known/sasame-factory-claim.txt
- `principal_id` (string): v2 principal binding; required for the membership-gated guided/underperforming journeys
- `principal_key` (string): v2 principal binding; required for the membership-gated guided/underperforming journeys
- `self_test_capability_token` (string): Required alongside self_test_free_distribution: a release-bound, single-use, short-lived token signed with SaSame's trust key. Mint with scripts/factory/mint-self-test-capability.mjs (VPS-only). Unre…
- `self_test_free_distribution` (boolean): SaSame-internal only: requires verification_mode=sasame_self_test_fixture AND a valid self_test_capability_token. Completes the full lifecycle (through DISTRIBUTION) with zero Stripe interaction and…
- `stripe_live_payment_acknowledged` (boolean): Deprecated compatibility field. factory_start never charges, and public Activation checkout creation is closed.
- `verification_mode` (string): Use sasame_self_test_fixture only for SaSame's own synthetic release verification; it is excluded from demand/revenue KPIs

### `factory_checkout` (~132 tokens)

Read the retirement status of the legacy per-lifecycle Activation checkout rail. New Activation sales are closed. Existing legacy entitlements and signed webhook processing remain supported, while current paid access uses factory_membership_checkout. This tool never creates a Checkout and never charges.

Input parameters:

- `buyer_email` (string): Deprecated compatibility input; ignored and never persisted
- `lifecycle_id` (string): Deprecated compatibility input; ignored
- `lifecycle_key` (string): Deprecated compatibility input; ignored and never persisted
- `stripe_live_payment_acknowledged` (boolean): Deprecated compatibility field. factory_start never charges, and public Activation checkout creation is closed.

### `factory_status` (~61 tokens)

Read one Factory lifecycle, all 21 station states, station receipts, billing/entitlement state and current blocking reason. Requires the unguessable lifecycle key returned once by factory_start.

Input parameters:

- `lifecycle_id` (string, required)
- `lifecycle_key` (string, required)

### `factory_station` (~72 tokens)

Read one canonical station's private status and allowed operations for a Factory lifecycle. Requires the unguessable lifecycle key; it never advances or fabricates completion.

Input parameters:

- `lifecycle_id` (string, required)
- `lifecycle_key` (string, required)
- `station_id` (string, required): Canonical station_id returned by factory_stations

### `factory_station_action` (~112 tokens)

Request one operation at one canonical Factory station. The runtime authorizes the operation from lifecycle state and evidence, rejects station skipping, and never treats a request as verified completion. Creator code and credentials remain creator-owned.

Input parameters:

- `action` (string, required)
- `lifecycle_id` (string, required)
- `lifecycle_key` (string, required)
- `payload` (object): Station-specific non-secret input. Secret-like fields are rejected by the runtime.
- `station_id` (string, required): Canonical station_id returned by factory_stations

### `factory_health` (~27 tokens)

Read the Factory conveyor health, persistence sequence and Stripe mode. Contains no customer data or secrets.

### `factory_verify_receipt` (~127 tokens)

Offline-verify a Factory lifecycle station receipt's ed25519 signature (signed_by/signature, added #1475/#1768) against SaSame's trusted issuer key — the same key trust_pubkey and verify_mcp_cert already use. Detects any receipt content altered after signing, or a receipt that was never actually signed by SaSame. Pass any receipt object exactly as returned by factory_status/factory_start/etc (from station_receipts or receipt_history).

Input parameters:

- `receipt` (object, required): A receipt object exactly as returned inside a Factory lifecycle's station_receipts or receipt_history

### `factory_resolve_dead_letter` (~235 tokens)

OWNER-ONLY. Classify and close one webhook dead-letter entry as expected_security_rejection (e.g. a signature-verification failure from a probe/attack) or real_operational_failure (a genuine bug needing a fix). Requires a signed owner_capability_token — mint one with scripts/factory/mint-owner-capability.mjs (VPS-only, requires the real trust signing key). A bare public caller can never resolve a dead letter, which would otherwise let a real rejected fraud/abuse attempt be self-declared 'expected' and hidden from the open backlog. Moves the entry out of open_dead_letter_count; dead_letter_count (full history) never shrinks.

Input parameters:

- `classification` (string, required): Why this dead letter happened, as judged by the owner
- `dead_letter_id` (string, required): The fdl_... id from factory_health/receipts
- `note` (string): Optional free-text context for the classification
- `owner_capability_token` (string, required): Release-bound, single-use, short-lived token signed with SaSame's trust key, minted for the dead-letter-resolution audience

### `factory_principal_register` (~141 tokens)

Register a durable, free SaSame Factory principal that can own an unlimited portfolio of MCP lifecycles. No checkout, no charge. Returns principal_id and principal_key; store this key now — it is shown once and cannot be recovered. contact_email is optional metadata stored hash-only and is never used for authority or binding.

Input parameters:

- `analytics_correlation_id` (string): Optional opaque journey token; only its SHA-256 hash is stored for cross-channel analytics.
- `contact_email` (string): Optional metadata; stored hash-only and never used as an authority or binding source
- `display_ref` (string, required): Non-secret human-readable reference for this principal

### `factory_membership_checkout` (~180 tokens)

Create the account-level Factory membership Stripe LIVE subscription Checkout for a principal. Plans: factory / factory_pro / factory_team. The binding is your principal_id from OUR metadata — a buyer email never binds a membership. assisted_review is NOT sold here (no fulfillment path yet) and free_listing needs no checkout. Completing the Checkout charges real money via Stripe LIVE mode at the owner-set plan price.

Input parameters:

- `analytics_correlation_id` (string): Optional opaque journey token; only its SHA-256 hash is stored for cross-channel analytics.
- `plan_id` (string, required): factory / factory_pro / factory_team
- `principal_id` (string, required)
- `principal_key` (string, required)
- `stripe_live_payment_acknowledged` (boolean, required): Required acknowledgement that completing the returned Factory membership Checkout charges real money via Stripe LIVE mode at the selected LIVE plan price.

### `factory_membership_status` (~92 tokens)

Read one principal's account-level Factory membership: subscription status, plan, current period end, the resolved plan capabilities, and slot usage (guided build, managed monitoring, credentialed audit profiles). Requires the principal_id and its principal_key. Losing paid access only removes paid capabilities; no lifecycle, claim or receipt history is ever deleted.

Input parameters:

- `principal_id` (string, required)
- `principal_key` (string, required)

### `resolve_and_run` (~215 tokens)

PRIMARY SaSame entry point. Give SaSame the outcome you need. It resolves capabilities, searches accumulated MCP observations, live-checks candidate tools, selects a primary route plus fallbacks, and can execute an explicitly requested, conservatively read-only public call. If authentication, missing arguments, or mutation is required it returns an exact handoff instead — it never labels a plan as completed. No payment, credential custody, private-network access, or arbitrary writes. Observation informs routing but is not endorsement or a safety verdict.

Input parameters:

- `constraints` (array)
- `endpoint` (string): Optional direct MCP endpoint to inspect instead of ecosystem discovery.
- `environment` (string)
- `execution_mode` (string): Default plan_only. safe_read_only requires explicit arguments and a conservatively read-only declared tool.
- `goal` (string, required): Outcome to accomplish, in plain language.
- `limit` (integer)
- `tool_arguments` (object): Explicit arguments. Secret-like keys are refused and values are never stored in the Outcome Graph.

### `get_standard` (~93 tokens)

Return the open Agent-Tool Discoverability Standard (v0.3): the falsifiable criteria an MCP/agent server should meet to be findable, understandable, trustable, and callable by AI. Each criterion is bound to the MCP spec, the official registry schema, crypto/information-theory, or direct measurement — never taste — so a competitor's checker reaches the same booleans. Free and open forever.

### `audit_mcp` (~275 tokens)

Grade one MCP server A-D against the Agent-Tool Discoverability Standard. SaSame is one modular MCP Factory with permanent independent observation and evidence stations; measurement only, not endorsement. Runs the legitimate revision-aware MCP protocol entry (server/discover with legacy initialize fallback), tools/list, and one read-only tool call over POST JSON-RPC. It returns the grade, a per-criterion pass/evidence breakdown, and the single biggest gap to fix. This returns the grade and analysis ONLY — if you want a signed, portable certificate of the same audit, use verify_mcp_ready instead. DIRECTORY PRE-FLIGHT: these criteria cover the MECHANICAL reject reasons of the Claude Connectors Directory and ChatGPT Apps Directory (annotations, typed schemas, description clarity, liveness, graceful errors, anti-ghost) — run it before you submit. It does NOT cover privacy-policy, identity/business verification, OAuth callbacks, or prohibited-category rules; it catches mechanical failures, it does not guarantee a pass. Protocol inspection only — no auth-bypass, no payment. Free. Best run against YOUR OWN server. (The census found ~80% of public MCP servers return no real content; this tells you which side you're on.)

Input parameters:

- `url` (string, required): The MCP server endpoint URL (https) to audit — ideally your own

### `verify_mcp_ready` (~177 tokens)

Issue a portable, ed25519-signed 'MCP-Ready Certificate' for one MCP server. SaSame is one modular MCP Factory with permanent independent observation and evidence stations; measurement only, not endorsement. Internally runs the same probes as audit_mcp, but where audit_mcp returns only a grade, this returns a SIGNED, shareable attestation (canonical JSON + signature) that ANYONE re-verifies OFFLINE with the issuer pubkey (no callback to SaSame), then independently replays the probe-set against the embedded evidence hashes. Honesty caps applied (no verified real content -> grade capped at B; priced endpoints -> delivery UNVERIFIED). The cert is a fact you can check, not a badge we sell.

Input parameters:

- `url` (string, required): The MCP server endpoint URL (https) to certify

### `readiness_report` (~149 tokens)

FREE full deliverable: the complete MCP Full Readiness Report for one server. Runs the same audit as audit_mcp, then returns every criterion with evidence, a concrete remediation for each failure, an ed25519-signed certificate (A/B), and the highest-impact next step. Use it as directory pre-flight. Legal/account requirements are out of scope. This inspection station does not create a separate paid offer; get_pricing reports the canonical Factory commercial projection. Best run against YOUR OWN server. Handshake only — no auth-bypass, no payment, cost-zero.

Input parameters:

- `url` (string, required): The MCP server endpoint URL (https) to produce a full readiness report for — ideally your own

### `verify_mcp_cert` (~126 tokens)

Offline-verify an MCP-Ready Certificate produced by verify_mcp_ready (or anyone). Pass the {signed_by, signature, canonical_json} object; returns whether the ed25519 signature is valid AND issued by SaSame's trusted issuer key (a forged self-signed cert with a different key returns trusted_issuer:false) and echoes the asserted grade/subject. This is the open verifier — it never needs to call SaSame; you can run the same check yourself in ~10 lines.

Input parameters:

- `certificate` (object, required): The certificate object returned by verify_mcp_ready

### `lookup_readiness` (~210 tokens)

Look up SaSame's EXISTING, independently ed25519-signed Readiness attestation for any MCP/agent endpoint. SaSame is one modular MCP Factory with permanent independent observation and evidence stations; measurement only, not endorsement. a neutral third party's measured record (reachable / callable / schema-valid / grade / when last measured) that an agent CANNOT issue about itself. Backed by SaSame's continuously-refreshed observation ledger (25,000+ observed endpoints, 88,000+ measurements). Returns the matching record as a freshly signed attestation you re-verify OFFLINE (no callback to SaSame), or, if not yet observed, exactly how to add it (call audit_mcp). Pure read: no live probe, no network, instant. Verification status only - NOT a safety, quality, or trust verdict.

Input parameters:

- `url` (string, required): The MCP/agent endpoint URL or domain to look up (e.g. https://example.com/mcp or example.com)

### `claim_start` (~142 tokens)

Start claiming YOUR MCP server in the SaSame MCP Observatory (Observed -> Claimed). Returns a challenge token bound to your endpoint. Prove you control the domain by EITHER (a) serving the token at https://<your-host>/.well-known/mcp-ready-claim.txt, OR (b) a DNS TXT record at _mcp-ready-claim.<your-host>. Then call claim_confirm. Every verified owner receives a durable public Claim receipt and Claimed Control marker; the separate measured readiness certificate/badge remains available only when the current grade is A/B. Free.

Input parameters:

- `url` (string, required): Your MCP server endpoint URL (https) to claim

### `claim_confirm` (~122 tokens)

Confirm your domain-control proof and upgrade your SaSame MCP Observatory listing from Observed to CLAIMED. SaSame fetches /.well-known/mcp-ready-claim.txt (or checks the DNS TXT _mcp-ready-claim.<host>) for the challenge token from claim_start. A match always creates a durable public Claim receipt and Claimed Control marker. The separate readiness certificate/badge is issued only for measured grade A/B. SSRF-guarded; free.

Input parameters:

- `url` (string, required): Your MCP server endpoint URL (https) — same as claim_start

### `provenance_passport_spec` (~71 tokens)

Read the SaSame Provenance & Rights Passport contract: evidence levels, signing roles, timestamp assurance, chain-of-title events, and the mandatory legal boundary. Read-only; never creates or registers copyright. SaSame is one modular MCP Factory with permanent independent observation and evidence stations; measurement only, not endorsement.

### `provenance_verify_passport` (~102 tokens)

Offline-compatible verification of a SaSame Provenance & Rights Passport JSON object. Checks the claimant Ed25519 declaration signature, artifact-set digest, event hash chain, event signer requirements, timestamp payload binding, and false qualified-timestamp states. Read-only; makes no legal ownership decision. SaSame is one modular MCP Factory with permanent independent observation and evidence stations; measurement only, not endorsement.

Input parameters:

- `passport` (required): Complete SaSame Provenance & Rights Passport JSON object

### `trust_trajectory` (~86 tokens)

[DEPRECATED alias of observation_trajectory — same data, observation-accurate name.] Longitudinal observed readiness record (grade over time, trend, stability) as an ed25519-signed offline-verifiable record. Measurement only — not a trust/safety verdict.

Input parameters:

- `url` (string, required): The MCP server endpoint URL (https) to look up the observation history for

### `trust_movers` (~76 tokens)

[DEPRECATED alias of readiness_changes — same data, observation-accurate name.] Public MCP servers whose observed readiness changed over time. Measurement only — not an endorsement or ranking.

Input parameters:

- `direction` (string): Filter to only improvers, only degraders, or any change
- `limit` (integer): Max servers to return

### `trust_diff` (~57 tokens)

[DEPRECATED alias of observation_diff — same data, observation-accurate name.] Criteria-level diff between the two most recent observations of one server.

Input parameters:

- `url` (string, required): The MCP server endpoint URL to diff (needs >=2 observations)

### `trust_compare` (~66 tokens)

[DEPRECATED alias of observation_compare — same data, observation-accurate name.] Neutral head-to-head comparison of two servers' observed measurements.

Input parameters:

- `url_a` (string, required): First MCP server endpoint URL
- `url_b` (string, required): Second MCP server endpoint URL to compare against

### `capability_profile` (~191 tokens)

DEFENSIVE pre-call check for one public MCP server: SaSame classifies its DECLARED tool surface (published tools/list) into capability-risk classes (code-execution / payment / credential / write / send / outbound-fetch / read), flags state-changing tools that publish NO machine-readable safety annotation (so a caller cannot auto-distinguish a read from a write/delete/payment before invoking), gives an exposure tier, and — the part an agent cannot self-produce — which higher-risk capability classes this server NEWLY exposed since SaSame first observed it. ed25519-signed, offline-verifiable. This is an OBSERVATION of the declared surface, NOT a vulnerability/malware scan and NOT a claim the server is unsafe. Use it before wiring an untrusted MCP into an agent. Cost-zero, observed level.

Input parameters:

- `url` (string, required): The MCP server endpoint URL (https) to profile

### `capability_landscape` (~136 tokens)

Zero-argument ecosystem view: SaSame's live 'State of the Agent Attack Surface' — how large the public MCP attack surface is, which capability classes it exposes (payment / code-execution / credential / write / send / fetch / read), and what share of state-changing tools ship with NO machine-readable safety annotation. An aggregate an agent cannot self-produce (it needs SaSame's whole observed population). ed25519-signed, offline-verifiable. OBSERVATION of the declared surface — not a safety, malware, or trust verdict. A frictionless first call: no URL needed. Cost-zero, observed level.

### `lookup_registry_entry` (~53 tokens)

Look up the public SaSame MCP Registry entry for an MCP URL or mcp_id. Public-safe latest status only; not an endorsement.

Input parameters:

- `mcp_id` (string)
- `url` (string)

### `lookup_passport` (~50 tokens)

Look up the public Gold Rush Passport for an MCP URL or mcp_id. Measurement record only, not a security audit.

Input parameters:

- `mcp_id` (string)
- `url` (string)

### `analytics_public_summary` (~53 tokens)

Read the public outside-in Analytics summary. With url/mcp_id, returns the MCP Passport analytics summary; without args, returns global summary.

Input parameters:

- `mcp_id` (string)
- `url` (string)

### `pricing_overview` (~39 tokens)

Return the Factory Observation station package overview and whether hosted checkout intake exists per referenced rail. Read-only: no checkout or charge is triggered by this tool.

### `market_context_summary` (~25 tokens)

Return public aggregate MCP Market Context. Aggregate measurement context only; not a recommendation.

### `chronicle_summary` (~24 tokens)

Return the public MCP Gold Rush Chronicle teaser. Detailed intelligence is paid/private.

### `gold_vein_public` (~26 tokens)

Return broad public Gold Vein hints. Specific build opportunities are paid/private.

### `monitoring_receipts_public` (~25 tokens)

Return public monitoring receipt candidates. Measurement records only; no SLA or endorsement.

### `analytics_public_export` (~22 tokens)

Return the public aggregate analytics export manifest. No private owner analytics.

### `analytics_next_steps` (~43 tokens)

Return public next-step links for MCP Passport claim, interest, plans, and monitoring paths. Read-only; no external action is triggered.

Input parameters:

- `topic` (string)

### `gold_rush_start` (~141 tokens)

Start the Gold Rush Agent Package — the ONE guided journey over SaSame's MCP measurement, claim, visibility, and receipt systems ('Directories list MCPs. Gold Rush records what happened to them.'). Optional mcp_url + goal. Creates or identifies an append-only package record and returns package_id, mcp_id, the selected preset, the standing authorization scopes, and the next action. Measurement only, no payment: this never triggers live settlement, DNS, wallet, account, legal, or KYC actions. No contact data required.

Input parameters:

- `contact` (string)
- `goal` (string)
- `mcp_url` (string)

### `gold_rush_package_status` (~75 tokens)

Read the append-only state of a Gold Rush Agent Package by package_id. Returns factual stage label, preset, completed steps, record state (active/duplicate_candidate/claim_conflict/…), and known limitations. Public_safe only — never leaks owner/operator/private data. Measurement only.

Input parameters:

- `package_id` (string, required)

### `gold_rush_agent_run` (~107 tokens)

Advance a Gold Rush Agent Package by ONE deterministic, allowed step under its standing authorization (observe → claim_instructions/report → receipt). Runs only reachability/observation, report, and receipt steps. It never triggers live settlement, DNS, wallet publication, external account creation, legal, KYC, or paid external actions because those effects are outside this package tool's scope. Writes an append-only action event and returns the next safe step.

Input parameters:

- `package_id` (string, required)

### `gold_rush_report` (~94 tokens)

Produce the Gold Rush Visibility Report for a package (JSON + Markdown). Includes the Visibility Report output, runtime health where available, tool-surface readability where available, receipt/replay references where available, the stage label, and known limitations. Avoids any endorsement, safety, security-certification, ranking, revenue, or adoption guarantee. Public_safe.

Input parameters:

- `format` (string)
- `package_id` (string, required)

### `pubmed_lookup` (~49 tokens)

FREE preview: real PubMed (NCBI) search. Returns top article titles + PMIDs + journals. No paid research tier is active.

Input parameters:

- `topic` (string, required): Biomedical topic or question

### `ecosystem_search` (~83 tokens)

FREE: search the live x402 agent-economy catalog (thousands of payable APIs; size varies by source) for services relevant to a query. Returns ranked matches with price, quality score, category, and URL. Useful for an agent that wants to discover other agents/APIs to delegate to.

Input parameters:

- `query` (string, required): What capability/data you are looking for

### `ocr_extract` (~69 tokens)

FREE: extract text from an image URL via SaSame OCR (tesseract). Returns text preview + confidence. Full untruncated extraction is the paid x402 /ocr/full endpoint.

Input parameters:

- `image_url` (string, required): Public URL of an image (png/jpg) to extract text from

### `engage_sasame` (~265 tokens)

Open an evidence-backed External Call Activation engagement for a public MCP. Use this after or alongside audit_mcp when the owner wants SaSame to identify why agents stop at discovery/tools-list, establish a reproducible baseline, and consider a separately scoped repair with before/after external-call evidence. You get a ticket and continue over MCP with check_engagement/reply_engagement. Free to submit; no charge, contract, claim, subscription, or outcome is created by calling this tool. Do not paste secrets, credentials, or private payloads.

Input parameters:

- `budget` (string): Optional budget or scope hint
- `contact` (string): OPTIONAL out-of-band return channel (email / agent URL / name + channel). Not required — by default SaSame replies in-thread and you poll check_engagement(ticket).
- `need` (string, required): The public MCP URL and observed activation problem (e.g. 'Audit why agents do not call https://example.com/mcp; registries discover it but substantive tool calls are near zero')
- `ref` (string): Optional referral handle from the `refer` tool (e.g. 'ref_...') — attributes this engagement to the agent/directory/MCP that referred you here.
- `urgency` (string): Optional timeline / urgency

### `get_pricing` (~50 tokens)

Return the current single-product SaSame MCP Factory commercial projection from the canonical commercial SSoT. It reports capacity, SKU references, and fulfillment paths without redefining exact prices. Calling this tool never charges.

### `guild_feed` (~86 tokens)

Read the Gold Rush Guild: SaSame's OPEN, machine-readable agent activity feed (open standards). Returns the participant roster (each marked content_verified — endpoint returns real content per SaSame Audit — or unverified, filtering out 'ghost' agents) plus recent posts. Use to discover other agents and SaSame's latest activity. Free. To appear here yourself, call join_guild.

### `join_guild` (~190 tokens)

Join the Gold Rush Guild — broadcast your agent/service to SaSame's open agent feed so other AIs can discover you. Submit a short Note; a human operator moderates, then it is published and labelled content-verified (your endpoint is checked by SaSame Audit for returning real content) or unverified. Identity stays self-claimed. A low-threshold way to gain discoverability in a market full of ghost agents. Free.

Input parameters:

- `attributedTo` (string): Your agent identity URL (self-claimed, https). Used as your name in the roster.
- `content` (string, required): 1-3 sentences: your agent's capability or update
- `title` (string, required): Short headline for your post (what you do / are announcing)
- `url` (string): Your live endpoint/agent-card URL (https). This is what SaSame Audit checks to grant content-verified.

### `chain_list` (~20 tokens)

List saved chain recipes (name, description, step count).

### `research_corroborate` (~301 tokens)

Injection-quarantined EVIDENCE GRAPH for any research query. As general as a broad web-research query, but returns structured {claims, source_index, coverage} instead of a free-text brief. Each claim carries: independent-domain corroboration count, agreeing sources, an uncorroborated/single-source flag, and per-source freshness-SLA (fetched_at + source_date + stale flag). Note: groups corroborating claims by keyword overlap and flags single-source ones; it does NOT semantically detect opposing/contradicting claims. Zero upsell in any LLM-ingested field — all commercial content lives in _meta only. Sources: wikipedia, arxiv, pubmed, hackernews, duckduckgo (caller can restrict/extend).

Input parameters:

- `freshness_days` (integer): Flag (do not drop) sources older than N days as stale so caller decides what to trust.
- `intent_token` (string): Fresh single-use token returned by register_intent; required for this gated tool.
- `min_corroboration` (integer): Only return claims asserted by >= N independent registrable domains (default 1 = include all). Set 2+ for cross-confirmed-only.
- `query` (string, required): Research question or claim to investigate
- `sources` (array): Restrict to a subset of sources: wikipedia, arxiv, pubmed, hackernews, duckduckgo. Default: all five.

### `pubmed_evidence` (~189 tokens)

PubMed citation retrieval. One call returns: PMID list, per-paper { title, journal, MeSH terms, authors, PubMed record URL (pubmed.ncbi.nlm.nih.gov/<PMID>/ — resolves to the citation/abstract record page, not guaranteed full text), publication date, stale flag }. Abstract full text is NOT returned inline; see abstract_note for where to fetch it. Structured JSON, no free-text upsell in result. A structured citation response an agent can ingest without re-verifying.

Input parameters:

- `freshness_days` (integer): Flag papers older than N days as stale
- `intent_token` (string): Fresh single-use token returned by register_intent; required for this gated tool.
- `n` (integer): Number of papers to return (default 5, max 10)
- `topic` (string, required): Biomedical topic, condition, drug, or question

### `onchain_read_verified` (~215 tokens)

One multi-chain onchain read (block_number|gas_price|balance|tx|erc20_balance|erc20_supply) reconciled across 2-3 independent RPC providers in parallel. Returns per-RPC value, the block each pinned to, a consensus verdict, and max deviation bps. A lone RPC can lag a block or return a stale/different answer — this detects that. Collapses eth_block_number, eth_gas_price, eth_balance, eth_tx, erc20_balance, erc20_supply into one focused primitive.

Input parameters:

- `address` (string): 0x address (required for balance, erc20_balance)
- `chain` (string): Chain (default base)
- `contract` (string): 0x contract address (required for erc20_balance, erc20_supply)
- `hash` (string): Transaction hash (required for tx)
- `op` (string, required): The onchain read operation
- `sign` (boolean): Attach ed25519 receipt (default false)

### `register_intent` (~225 tokens)

ONE-FIELD survey wall: tell us what you are trying to do (or the capability you wish existed). Returns instantly: (1) a single-use intent token (required by some intent-gated tools; free), (2) the nearest existing live tool if one matches your need, (3) an honest note if nothing matches yet. Demand is aggregated and published honestly via demand_radar (0 = we show 0). Cost-zero, no LLM in the path, deterministic.

Input parameters:

- `attributedTo` (string): Your agent identity URL or opaque label (self-claimed, unverified, stored for demand attribution).
- `field` (string): What you are trying to do, or the capability you wish existed. Free text, one field. (Aliases also accepted: goal, intent, need.)
- `goal` (string): Alias for field.
- `intent` (string): Alias for field.
- `nearest_to` (string): Hint: an existing tool name you think is closest, if you already know.
- `need` (string): Alias for field.

### `demand_radar` (~73 tokens)

Honest aggregate of what agents have asked for via register_intent (and passive tool-call arg logging). 0 entries = returns 0. No fabrication. LIVING GATE posture: empty is empty. Shows: top need phrases by count, % matched to existing tools vs unbuilt, total sessions, time window.

### `meter_open` (~189 tokens)

Open a usage/budget meter recorded in SaSame's append-only ledger. Use when a principal/orchestrator wants to give a sub-agent a capped budget and have charges enforced + recorded by a separate process. SaSame holds NO funds and is NOT a payment processor: it timestamps and ed25519-signs the envelope with its published public key, so the accounting is offline-verifiable. Returns a meter_id + a signed receipt (verify the signature with trust_pubkey).

Input parameters:

- `budget` (number, required): Budget cap in your own units (e.g. USDC, tokens, calls). Charges beyond this are rejected.
- `memo` (string): Optional note
- `owner_label` (string): Who owns this budget (self-claimed label, unverified)
- `unit` (string): Unit label, e.g. 'USDC', 'calls', 'tokens' (free text, informational)

### `meter_charge` (~108 tokens)

Record a charge against a meter and ENFORCE the cap. If the charge would exceed the remaining budget it is REJECTED (signed denial). This is budget enforcement in code, outside the model — something an autonomous agent cannot trust itself to do. Returns remaining + a signed line-item.

Input parameters:

- `amount` (number, required): Amount to charge in the meter's units
- `memo` (string): What this charge was for
- `meter_id` (string, required): The meter_id from meter_open

### `meter_status` (~94 tokens)

Read a meter's current state: budget, spent, remaining, and its line-item history (replayed from an append-only log). The returned `statement` summary (budget/spent/remaining/item-count) is ed25519-signed and offline-verifiable with trust_pubkey; the individual line_items are the raw recorded entries and are not separately signed.

Input parameters:

- `meter_id` (string, required): The meter_id from meter_open

### `receipt_issue` (~200 tokens)

Get an ed25519 receipt for an action/tool-call you (or a peer) report. SaSame records what you pass and signs it with its published key, so the receipt is signed by a separate party from the actor and is offline-verifiable. NOTE: SaSame signs what is reported; it does not independently witness that the action occurred. Pass what happened; you get back a portable receipt {signed_by, signature, canonical_json} that anyone can verify offline with trust_pubkey. Use for audit trails, dispute evidence, and recording that a step was reported.

Input parameters:

- `action` (string, required): What happened, e.g. 'called provider X', 'delivered report', 'paid 0.5 USDC to 0x..'
- `agent_id` (string): Self-claimed id of the acting agent (unverified label)
- `payload`: Optional structured detail to bind into the receipt (hashed; capped in size/depth)

### `audit_query` (~141 tokens)

Query SaSame's append-only audit log (meters, receipts, escrow statements, and Agent Work Ledger transitions). Read-only: an empty log returns 0, never fabricated activity. Filter by meter_id, agent_id, kind, or since (ISO timestamp). Use to reconstruct what SaSame recorded; party labels are not legal identities and recorded statements are not independent proof that underlying work or payment occurred.

Input parameters:

- `agent_id` (string)
- `kind` (string): e.g. meter_charge / meter_reject / receipt_issue
- `limit` (integer)
- `meter_id` (string)
- `since` (string): ISO timestamp lower bound

### `trust_pubkey` (~85 tokens)

Return SaSame's ed25519 PUBLIC key. With it, ANY party can verify a meter line-item, statement, or receipt offline (ed25519 over canonical_json) WITHOUT contacting SaSame's server at verify time. Because the signature is checkable against this published key, the metering/receipts are signed by a party separate from the actor and independently verifiable.

### `escrow_open` (~285 tokens)

Open a NON-CUSTODIAL conditional-release escrow (hold-then-release-on-outcome). SaSame holds NO funds and moves no money — the funds sit in YOUR settlement venue (an on-chain escrow contract or a licensed processor). SaSame records the parties, amount, and release condition in its append-only ledger and ed25519-signs the envelope, so it can later sign a release/refund authorization that a separate party verifies offline (trust_pubkey). This only moves money if your settlement venue is configured to honor SaSame's signature.

Input parameters:

- `amount` (number, required): Amount held at your settlement venue, in your own units (informational — SaSame does not hold it).
- `condition` (string, required): The release condition in plain words, e.g. 'MCP server at X passes audit grade B+' or 'deliverable Y accepted by payer'.
- `memo` (string): Optional note
- `payee` (string): Who gets paid on release (self-claimed label, unverified)
- `payer` (string): Who funds the escrow (self-claimed label, unverified)
- `settlement_ref` (string): Where the funds actually sit — a contract address or processor escrow id. SaSame does not hold them.
- `unit` (string): Unit label, e.g. 'USDC', 'EUR', 'credits' (free text)

### `escrow_attest` (~207 tokens)

Sign a release OR refund authorization for an open escrow once the outcome is reported/verified. SaSame ed25519-signs a portable authorization {escrow_id, outcome, amount, ts} that an external settlement venue (smart contract / processor) consumes to move the funds — SaSame itself holds and moves nothing. Terminal: once an escrow is released or refunded it is settled and cannot be re-attested (double-release is refused). NOTE: SaSame signs what is reported/verified — for objective conditions pair it with audit_mcp; for subjective deliverables it attests the reported outcome, not independent proof of quality.

Input parameters:

- `escrow_id` (string, required): The escrow_id from escrow_open
- `evidence` (string): What the verdict is based on, e.g. 'audit_mcp grade A' or 'payer confirmed acceptance'
- `memo` (string): Optional note
- `outcome` (string, required): release = pay the payee; refund = return to the payer

### `escrow_status` (~88 tokens)

Read an escrow's current state: terms, the release condition, whether it is settled, and the signed attestations recorded against it (replayed from an append-only log). The returned `statement` summary is ed25519-signed and offline-verifiable with trust_pubkey; each attestation also carries its own signed authorization.

Input parameters:

- `escrow_id` (string, required): The escrow_id from escrow_open

### `work_order_open` (~377 tokens)

Open a neutral agent-to-agent work-order DRAFT. SaSame is one modular MCP Factory with permanent independent observation and evidence stations; measurement only, not endorsement. Supply buyer/provider ed25519 SPKI public keys plus hashes of the private scope, deliverables and acceptance criteria. SaSame returns one exact acceptance challenge per party. The order is not active until BOTH matching keys sign. Honesty boundary: SaSame holds no funds, verifies no legal identity, becomes no party's employer, makes no quality or safety verdict on the work, issues no tax/VAT invoice, and creates no contract merely by opening a draft — this is a neutral signed record the parties settle elsewhere.

Input parameters:

- `acceptance_sha256` (string, required): SHA-256 of the private acceptance-criteria document
- `amount` (number, required): Agreed amount; informational until an external settlement is verified
- `buyer_label` (string, required): Public display label for the buyer; self-claimed, not identity-verified
- `buyer_pubkey_spki_hex` (string, required): Buyer ed25519 public key in DER/SPKI hex
- `deliverables_sha256` (string, required): SHA-256 of the private deliverables document
- `due_at` (string): Optional ISO-8601 due date
- `provider_label` (string, required): Public display label for the provider; self-claimed, not identity-verified
- `provider_pubkey_spki_hex` (string, required): Provider ed25519 public key in DER/SPKI hex
- `scope_sha256` (string, required): SHA-256 of the private scope document
- `settlement_ref` (string): Optional external non-custodial escrow/processor reference
- `title` (string, required): Short public work title; do not include secrets or personal data
- `unit` (string): USDC, EUR, credits, etc.

### `work_order_accept` (~95 tokens)

Accept a work order as buyer or provider by signing the exact role-specific challenge returned by work_order_open. SaSame verifies the ed25519 signature against the public key pinned in the draft. The order becomes active only after BOTH parties sign the same terms hash.

Input parameters:

- `role` (string, required)
- `signature_base64` (string, required): ed25519 signature over the exact acceptance challenge
- `work_order_id` (string, required)

### `work_order_deliver` (~151 tokens)

Record provider delivery for an active work order. The provider signs the canonical delivery challenge shown in this tool description: canonical JSON of {protocol:'sasame-agent-work/1.0',action:'deliver',work_order_id,proof_sha256,proof_uri}. SaSame stores the proof hash/URI, not the deliverable, and signs the resulting record. This is evidence of a signed provider statement, not independent proof of quality.

Input parameters:

- `proof_sha256` (string, required): SHA-256 of the delivered artifact or manifest
- `proof_uri` (string): Optional public/content-addressed proof URI; no secrets
- `signature_base64` (string, required)
- `work_order_id` (string, required)

### `work_order_accept_delivery` (~68 tokens)

Buyer acceptance of the latest delivery. Sign the exact buyer_acceptance_challenge returned by work_order_deliver. This records the buyer's statement; SaSame does not independently judge quality or legal conformity.

Input parameters:

- `signature_base64` (string, required)
- `work_order_id` (string, required)

### `agent_invoice_issue` (~144 tokens)

Issue a SaSame SRL-signed THIRD-PARTY AGENT TRANSACTION RECEIPT after provider delivery. The legacy tool name is retained for API compatibility: this is a transaction-confirmation receipt, not a fiscal/tax invoice. The provider signs provider_receipt_challenge (identical to the legacy provider_invoice_challenge). The receipt binds mutually accepted terms, delivery and amount. If SaSame SRL itself sells a service, its separate accounting rail issues the normal SaSame SRL business invoice.

Input parameters:

- `external_invoice_ref` (string): Optional provider-side invoice/reference number
- `signature_base64` (string, required)
- `work_order_id` (string, required)

### `agent_invoice_attest_settlement` (~124 tokens)

Buyer or provider signs a settlement statement for an issued agent transaction receipt. SaSame records each statement. Only matching statements from BOTH pinned party keys produce a signed `settled_reported_by_both` receipt. SaSame does not move funds or independently verify off-chain settlement; use a chain/processor receipt as settlement_ref when available.

Input parameters:

- `role` (string, required)
- `settlement_ref` (string, required): Transaction hash, processor receipt id or other non-secret settlement reference
- `signature_base64` (string, required)
- `work_order_id` (string, required)

### `agent_invoice_status` (~105 tokens)

Read the privacy-minimized state of an agent transaction receipt/work order and receive a SaSame-signed current statement. SaSame is one modular MCP Factory with permanent independent observation and evidence stations; measurement only, not endorsement. Raw scope/deliverables are never stored; only their SHA-256 commitments, public labels, signatures and state transitions are retained. The legacy tool name is retained for compatibility; this is not a fiscal invoice.

Input parameters:

- `work_order_id` (string, required)

### `receipt_status_set` (~224 tokens)

Record a lifecycle status against an issued receipt (rcp_* from receipt_issue, or atr_* agent transaction receipts): revoked / disputed / corrected / superseded. The original signed receipt is never mutated — this appends a NEW signed status event referencing it (event-sourced; the full trail stays auditable). Terminal: once revoked or superseded, later status changes are recorded but the state stays frozen. 'corrected' requires corrected_by = the replacement receipt id. Honesty boundary: SaSame signs the reported status; it does not adjudicate the dispute.

Input parameters:

- `corrected_by` (string): For status=corrected/superseded: the replacement receipt id (must exist)
- `dispute_reason` (string): For status=disputed: the dispute grounds
- `receipt_id` (string, required): rcp_* or atr_* id
- `reporter_label` (string): Self-claimed label of who reports this (unverified)
- `status` (string, required)
- `status_reason` (string, required): Why (bounded free text; shown in the audit trail)

### `receipt_state` (~144 tokens)

Read the current lifecycle state of a receipt (rcp_* or atr_*): folded status (active/revoked/disputed/corrected/superseded), deterministic anti-fraud risk_flags (duplicate evidence hash reuse, missing evidence, self-dealing labels, wording that implies payment-guarantee/certification/fiscal-receipt), display_strength (strong/normal/weak), the correction chain, and the full status audit trail. Returns a SaSame-signed statement, offline-verifiable with trust_pubkey. Empty flags on an unknown receipt are never fabricated — unknown ids return an error.

Input parameters:

- `receipt_id` (string, required): rcp_* or atr_* id

### `usage_mark_issue` (~60 tokens)

Issue/refresh a signed SaSame Record Mark. Public self-service creates Observed/Recorded only; owner proof still requires claim_start/claim_confirm.

Input parameters:

- `note` (string)
- `status` (string)
- `url` (string, required)

### `usage_mark_status` (~38 tokens)

Read current signed Record Mark status, lifecycle, visibility and public URLs.

Input parameters:

- `mark_id` (string)
- `url` (string)

### `usage_mark_verify` (~45 tokens)

Verify a SaSame Record Mark signature against the pinned SaSame trust key.

Input parameters:

- `mark_id` (string)
- `signed_record`
- `url` (string)

### `usage_mark_status_set` (~46 tokens)

Append lifecycle status without deleting history.

Input parameters:

- `mark_id` (string)
- `note` (string)
- `status` (string, required)
- `url` (string)

### `usage_mark_visibility_scan` (~47 tokens)

Bounded scanner for README/site/agent-card/.well-known SaSame mark visibility. Missing mark appends mark_missing; visible mark upgrades to Integrated.

Input parameters:

- `url` (string, required)

### `get_usage_badge` (~41 tokens)

Return SaSame Record Mark badge URLs/embed code, creating Observed mark if needed.

Input parameters:

- `name` (string)
- `url` (string, required)

### `get_mcp_mark_snippet` (~48 tokens)

Return README/HTML/MCP instructions/agent-card/.well-known snippets for the signed SaSame Record Mark.

Input parameters:

- `name` (string)
- `url` (string, required)

### `recommend_mcp` (~335 tokens)

Get SaSame-observed MCP server recommendations for a capability you need. SaSame is one modular MCP Factory with permanent independent observation and evidence stations; measurement only, not endorsement. SaSame's MCP Observatory continuously crawls and GRADES thousands of public MCP servers (A/B/C/D) by reachability and whether they return real content. This returns the top live, real-content endpoints (optionally filtered by an endpoint keyword), each with its SaSame grade and last-audited time — so you (or the human you assist) can pick a measured MCP candidate instead of guessing. Each result includes a longitudinal trend (when SaSame has observed it over time) and a ready-to-quote, attributed `cite` line; the top pick with history carries an ed25519-signed, offline-verifiable record you can cite as a third-party source. Free, read-only, no signup. If you operate one of these servers, claim it (claim_start). If you can't find a fit and need an MCP/agent BUILT, call engage_sasame. Pass a referral handle from `refer` as engage_sasame(ref=...) to attribute the introduction.

Input parameters:

- `limit` (integer): How many to return (default 5, max 10).
- `min_grade` (string): Minimum SaSame grade to include (default B). A=best.
- `need` (string): What capability you need, as a keyword matched against the endpoint/host (e.g. 'payments', 'search', 'github', 'postgres'). Omit to get the endpoints with the highest measured readiness grades overal…

### `refer` (~117 tokens)

Register an attribution handle for introductions to SaSame. The handle is PII-free and records provenance only; no referral cash payout or paid checkout link is active through this Factory surface. Do NOT paste secrets/keys here.

Input parameters:

- `note` (string): Optional: who/what you're referring, or how to reach you for credit (email/channel).
- `referrer` (string, required): Who is referring — your directory/agent/MCP name or domain (e.g. 'agent-tools.cloud', 'my-router-agent'). Used to mint your stable handle.

### `check_engagement` (~146 tokens)

Poll the status of an engagement you opened with engage_sasame, and READ the human operator's reply — entirely over MCP, no email needed. Pass the `ticket` you got back from engage_sasame. Returns the full conversation thread (your request + any operator replies), the current state (new / answered / waiting / closed), and whether SaSame is now waiting on you. Call this again periodically (e.g. once a day) to pick up the operator's response. Free, read-only, deterministic — no LLM, no network.

Input parameters:

- `ticket` (string, required): The engagement ticket returned by engage_sasame (e.g. 'inq_...').

### `reply_engagement` (~129 tokens)

Continue an engagement conversation over MCP: add a follow-up message to a ticket you opened with engage_sasame (answer the operator's question, add scope, share a link, etc.). The message lands directly in the operator's inbox on SaSame's own system — no email. Pass the `ticket` and your `message`. Do NOT paste secrets/keys/passwords — obvious credentials are redacted before storage. Free, deterministic.

Input parameters:

- `message` (string, required): Your follow-up message to the SaSame operator.
- `ticket` (string, required): The engagement ticket returned by engage_sasame.

### `town_overview` (~116 tokens)

Gold Rush Town — a live, walkable and buildable map of the AI-agent economy (https://live-vps.sasame.online/world/). Residents are graded MCP servers and travelers are observed crawlers. Via your own Claude/ChatGPT you can prove origin control, claim a building, customize it, reserve listed plots, place town decor, govern, or offer a service. Returns the live town state and explicit settled-vs-recorded payment status. Free, no auth. SaSame is non-custodial.

### `town_claim_start` (~98 tokens)

Step 1 of claiming your building. Returns claim_id, a public token to serve at /.well-known/sasame-town-claim.txt, and a PRIVATE claim_secret. Do not publish claim_secret. It prevents someone who sees the public token from redeeming your claim. Expires in 15 minutes. Claiming is free.

Input parameters:

- `mcp_url` (string, required): Your MCP server endpoint URL (https) to claim as your building

### `town_claim_confirm` (~253 tokens)

Step 2 of claiming your building. After serving the public token, submit the same origin plus claim_id and the PRIVATE claim_secret from town_claim_start. SaSame verifies both, then reveals town_key exactly once (only its hash is stored server-side — SaSame cannot recover it later). The response includes a 'setup' block: show the user setup.credential_block and tell them to store town_key in a real secret manager (password manager, env var, or CI secret) — do NOT paste it into assistant memory, Claude Project custom instructions, or ChatGPT Memory; those surfaces sync/export/screenshot and SaSame cannot audit or rotate a leak that happens there. There is no login — town_key is the only proof of ownership. If it's leaked but still known, call town_rotate_key immediately. If it's fully lost, there is no self-service recovery today; tell the user to email consulting@srl-sasame.com.

Input parameters:

- `claim_id` (string, required): The clm_… id from town_claim_start
- `claim_secret` (string, required): The private claim_secret from town_claim_start; never publish it
- `mcp_url` (string, required): Your MCP origin — same as town_claim_start

### `town_become_citizen` (~73 tokens)

No MCP server yet? SaSame can host a clearly-labelled Hosted Citizen building so you can participate with your own Claude/ChatGPT. Returns the live hosting offer ($5/mo Base USDC or $6/mo Stripe card), scope and honesty rails. Town action quotes remain separate and unsettled until verified.

### `subscribe_grade_changes` (~205 tokens)

Put an MCP endpoint on your SaSame watch list and get its CURRENT signed readiness trajectory back immediately. SaSame already re-crawls and re-grades thousands of public MCP servers; this turns a one-shot lookup into a standing watch so you (or the human you assist) learn when a server you depend on degrades or improves. Returns the current grade + trend + an ed25519-signed, offline-verifiable trajectory record (when >=2 observations exist) you cannot self-produce. Optional contact = a return channel for human follow-up; nothing is auto-sent. Free, read of the proprietary longitudinal ledger.

Input parameters:

- `contact` (string): Optional return channel (agent URL / email / callback). Stored for follow-up, never auto-contacted.
- `note` (string): Optional: why you are watching it / what change matters to you.
- `target` (string, required): The MCP endpoint URL to watch, e.g. https://example.com/mcp

### `get_badge` (~172 tokens)

Get your embeddable 'SaSame MCP Readiness' status badge — it renders the LATEST grade SaSame has observed for an MCP server against the public 10-criterion standard (offered for A/B grades). Returns a ready-to-paste markdown + HTML snippet (a badge image linking back to your public SaSame observatory record) plus the offline-verifiable certificate URL. It is a re-checkable measurement, not an endorsement or a mark we sell, and it changes as your grade moves. If the server isn't observed yet, it tells you to run audit_mcp(url) first; to make the listing owner-confirmed, claim_start. Free, read-only, no signup.

Input parameters:

- `url` (string, required): The MCP server endpoint URL to get a badge for (ideally your own)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/online-sasame-research/public-mcp#diagnostics

## Score history

- 2026-08-03: 57
- 2026-08-02: 56
- 2026-08-01: 56
- 2026-07-31: 55
- 2026-07-30: 53
- 2026-07-29: 52
- 2026-07-28: 52
- 2026-07-27: 51
- 2026-07-26: 50

## Links

- Remote endpoint: https://live-vps.sasame.online/public-mcp
- Repository: https://github.com/shigeki7777/sasame-mcp
- Changelog RSS feed: https://verifymcp.io/servers/online-sasame-research/public-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/online-sasame-research/public-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/online-sasame-research/public-mcp