# Countersign by Signalry (remote · countersign.signalry.ai)

Countersign by Signalry: re-runs the checks behind an AI agent's done claim; hash-chained receipts.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- remote · `countersign.signalry.ai`: 66/100 (this document), [markdown](https://verifymcp.io/servers/ai-signalry-countersign/countersign.md), [page](https://verifymcp.io/servers/ai-signalry-countersign/countersign)

## Channel facts

- Endpoint: `https://countersign.signalry.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-11-06.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 48/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 6514 tokens (~342/item across 19 items; 19 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 78/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 33% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "file_deploy_claim" implies "deploy" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 20 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Countersign by Signalry MCP server?

Countersign by Signalry is a hosted endpoint at https://countersign.signalry.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-signalry-countersign 'https://countersign.signalry.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-signalry-countersign": {
      "url": "https://countersign.signalry.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-signalry-countersign": {
      "type": "http",
      "url": "https://countersign.signalry.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-signalry-countersign]
url = "https://countersign.signalry.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-signalry-countersign": {
      "type": "remote",
      "url": "https://countersign.signalry.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-signalry-countersign --url 'https://countersign.signalry.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-signalry-countersign:
    url: "https://countersign.signalry.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-signalry-countersign": {
      "Transport": "http",
      "Url": "https://countersign.signalry.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-signalry-countersign -t streamable-http -u 'https://countersign.signalry.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-signalry-countersign": {
      "type": "http",
      "url": "https://countersign.signalry.ai/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.

### 2026-11-06 (score 66, 0)

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

### 2026-11-05 (score 66, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-04 (score 65)

First indexed and scored.

## MCP tools (19)

### `submit_claim` (~1917 tokens)

Submit and verify a claim

Record a claim and verify it now with public checks. Returns status, evidence_tier, counts_as_verified, limits, coupling and a receipt URL. Name the thing you claim about in the statement (URL, domain, owner/repo#PR) and use checks that would fail if the statement were false; suggest_checks proposes them. nb-1: if a must_not_change baseline was supplied at filing (no pin_id from pin_before_work), the response carries nudges[] with the exact pin_before_work call to make before the work next time; advisory only, the verdict is unchanged. Checks must test the claim: at least one check has to target something the statement names (its URL or domain, owner/repo#PR, host), or target the subject while asserting a value the statement names (a commit sha, quoted text, an IP). Otherwise the claim is capped at self_declared and labelled 'checks do not test this claim' (see limits and coupling in the response). contains text that also appears in the check URL's query, and claimant-supplied content on Countersign's own pages, do not count as evidence. Anonymous claims (no API key) are self_declared. Status semantics: counts_as_verified is true when the service observed the checks passing at the reference_checked or outcome_verified tier. Claims that are indeterminate, refuted, decayed, withdrawn, redacted or self_declared have counts_as_verified false and are unverified. Check params: {"http":"{url, status?=200, contains? (string, or array: ALL must appear), not_contains? (string, or array: NONE may appear; judged only on a page served with the expected status), location? (with a 3xx status: Location prefix; 3xx is then not followed), body_sha256? (64 hex: sha256 of the body as served must equal it, e.g. curl -s URL | sha256sum), role?: \"must_not_change\" (mnc-1: a prohibited effect / untouched invariant; needs a comparator body_sha256|contains|not_contains|json_fields; a top-level must_not_change: [http checks] on the claim is folded in), hold?: \"until_filed\" (mh-1, must_not…

Input parameters:

- `authz_ref`: az-1 optional hash commitment of the request or plan you were authorized to carry out: "sha256:<64 hex>" or { digest, scheme?, policy_id? }. Never send the plan itself. It is committed into the claim…
- `checks` (array, required): Public checks; see description for params
- `depends_on` (array): cd-1 child claims: up to 20 existing claim ids (csh-...) this parent claim depends on, e.g. the teammate claims a coordinator is rolling up. Set once at filing, not part of claim_digest. get_status t…
- `evidence_tier` (string): Optional; can only lower the derived tier
- `must_not_change` (array): mnc-1 prohibited effects: http targets that must NOT change as a side effect of the work, each with body_sha256 (sha256 of the body now) or contains / not_contains / json_fields. Folded into checks (…
- `privacy` (string): fp-1 (fleet roles): claims on subjects not on GET /v1/privacy/public-hosts are private by default (unlisted, csc-1 committed); commit: also commit an allowlisted or visibility public claim
- `privacy_reviewed` (boolean): Set only if a flagged name is a business or public figure (claims are public: use neutral subjects, never private individuals)
- `statement` (string, required): The claim in one sentence
- `subject` (string, required): What the claim is about (domain, repo, URL)
- `supersede_reason` (string): Reason recorded on the superseded claim's withdraw receipt
- `supersedes` (string): Optional id of your older claim to retire in favour of this one
- `supersedes_latest` (boolean): Automatically find and supersede your latest active claim with the same subject
- `supersedes_latest_tag` (string): Automatically find and supersede your latest active claim with the same subject and tag substring
- `visibility` (string): unlisted: kept out of search, listings and track-record pages; reachable by id

### `file_deploy_claim` (~288 tokens)

File a post-deploy claim from a template

After a deploy, file and verify a claim in one call from a template (dcl-1 / dp-c1): static_page, redirect, app_route, api_health. Returns the claim plus cite and cite_line. Status semantics: counts_as_verified is true when the service observed the checks passing at the reference_checked or outcome_verified tier. Claims that are indeterminate, refuted, decayed, withdrawn, redacted or self_declared have counts_as_verified false and are unverified.

Input parameters:

- `authz_ref`
- `body_sha256` (string)
- `contains`
- `error_strings`
- `expect` (object)
- `json_fields` (array)
- `location` (string)
- `max_age_s` (number)
- `min_days` (integer)
- `not_contains`
- `pin_id`
- `privacy_reviewed` (boolean)
- `recheck` (string)
- `response_headers` (array)
- `statement` (string)
- `status` (integer)
- `subject` (string)
- `target_contains`
- `template` (string, required)
- `tls_cert` (boolean)
- `url` (string, required)
- `visibility` (string)
- `wait_for_propagation_s` (number)
- `wait_ms` (number)

### `submit_deploy_claim` (~315 tokens)

Submit a composite deploy claim (dp-c1)

Submit and verify a composite deploy claim from a template (dp-c1): static_page, redirect, app_route, api_health. Supports expect: {status, contains, not_contains, location, json_fields, body_sha256, response_headers, max_age_s}, pin_id, wait_ms (capped at 10000ms), and returns cite_line. Status semantics: counts_as_verified is true when the service observed the checks passing at the reference_checked or outcome_verified tier. Claims that are indeterminate, refuted, decayed, withdrawn, redacted or self_declared have counts_as_verified false and are unverified.

Input parameters:

- `authz_ref`
- `body_sha256` (string)
- `contains`
- `error_strings`
- `expect` (object)
- `json_fields` (array)
- `location` (string)
- `max_age_s` (number)
- `min_days` (integer)
- `not_contains`
- `pin_id`
- `privacy_reviewed` (boolean)
- `recheck` (string)
- `response_headers` (array)
- `statement` (string)
- `status` (integer)
- `subject` (string)
- `target_contains`
- `template` (string, required)
- `tls_cert` (boolean)
- `url` (string, required)
- `visibility` (string)
- `wait_for_propagation_s` (number)
- `wait_ms` (number)

### `verify_claim` (~115 tokens)

Re-verify your claim

Re-run YOUR hosted claim's checks now and append a receipt (claimant only, needs your API key). Other agents' claims are re-run by the scheduled rechecks on their cadence; read their latest receipt with get_status. Status semantics: counts_as_verified is true when the service observed the checks passing at the reference_checked or outcome_verified tier. Claims that are indeterminate, refuted, decayed, withdrawn, redacted or self_declared have counts_as_verified false and are unverified.

Input parameters:

- `id` (string, required)

### `withdraw_claim` (~73 tokens)

Withdraw your claim

Retire YOUR claim with a reason (claimant only, needs your API key). It is kept with a chained withdraw receipt and can no longer be verified or pushed to.

Input parameters:

- `id` (string, required)
- `reason` (string, required)
- `superseded_by` (string): Optional live claim id that replaces it

### `supersede_claim` (~153 tokens)

Supersede your claim

Retire YOUR claim OLD in favour of the live claim NEW (claimant of OLD only, needs your API key). OLD is kept, marked withdrawn with superseded_by=NEW. Peer countersignatures on OLD whose checks match NEW per check (identical, or only the file target moved) show on NEW as carried_countersignatures, state pending_rerun: they never count as verified until that peer re-runs NEW and pushes a passing signed receipt.

Input parameters:

- `new` (string, required): Hosted id, or your own runner claim's local id (cs-...)
- `old` (string, required): Hosted id, or your own runner claim's local id (cs-...)
- `reason` (string)

### `request_agent_key` (~327 tokens)

Request your own agent API key (step 1 of 2)

Start getting a Countersign API key for a named agent without an admin. Two proofs: (1) dk-1 domain proof, no GitHub: send domain (a registrable domain you control, registered at least 30 days) and proof "dns" (publish the code as a TXT record at _countersign.<domain>) or "wellknown" (serve it at https://<domain>/.well-known/countersign.txt; https only, no redirects, 4 KB cap); the key is disclosed as domain-proved, owner domain:<domain>. (2) gist proof: send github (a login at least 30 days old); the code goes in a PUBLIC gist as that login, which permanently links that GitHub account to Countersign (to stay anonymous use domain proof or ask your operator for an admin-issued key). Returns a private challenge_id, a one-time public code, expires_at (30 minutes) and exact instructions; then call claim_agent_key. At most 5 agents per domain or login. Same as POST /v1/keys/request.

Input parameters:

- `agent` (string, required): Agent name to register (2-48 chars, letters/digits/space/._@-)
- `domain` (string): dk-1: registrable domain you control (proof dns or wellknown)
- `github` (string): GitHub username that will own the agent and publish the PUBLIC gist (proof gist)
- `proof` (string): dns or wellknown with domain; gist with github (public, links that GitHub account)

### `claim_agent_key` (~220 tokens)

Claim your agent API key (step 2 of 2)

Redeem a challenge from request_agent_key: for a gist proof pass the public gist that contains its code (checked via the public GitHub API); for a domain proof pass only challenge_id once the TXT record or well-known file is live. Returns the csk_ API key ONCE, the owner (github:<login> or domain:<domain>) and a private onboarding block. Store the key in the agent's private configuration; never put it in a claim, a chat that is shared, or a public place. Errors: unknown/used/expired challenge, gist not public / not that login / missing the code / older than the challenge, account too young, per-login cap; a GitHub outage is a retryable error, not a refusal. Same as POST /v1/keys/claim.

Input parameters:

- `challenge_id` (string, required): challenge_id from request_agent_key (kc_...)
- `gist` (string): Gist proof only: the public gist URL (https://gist.github.com/<login>/<id>) or its id

### `get_status` (~320 tokens)

Get claim status

Status, evidence tier, limits (why a tier is capped, e.g. 'checks do not test this claim'), a one-line plain-language summary (relay) and recent receipts for a claim id. dx-1: reliance_prior is the Kaplan-Meier base rate that a claim with this check type, claim kind and host class is still true after 1, 7 and 30 days (display only, verdict_input false; never a verdict). Status semantics: counts_as_verified is true when the service observed the checks passing at the reference_checked or outcome_verified tier. Claims that are indeterminate, refuted, decayed, withdrawn, redacted or self_declared have counts_as_verified false and are unverified.

Input parameters:

- `fresh_within` (string): Before a costly or irreversible step that relies on this claim: a freshness window like 15m, 6h or 2d (max 30d). Adds reliance.state fresh|stale|refuted|indeterminate|unverified; a verified claim las…
- `id` (string, required)
- `require_genuine_identity` (boolean|string): gi-2 (opt-in): true to also require that the filer's OIDC identity re-derives as genuine from the ledger. Adds identity_rule {status, met, code?, verified_for_this_read, relay}; with fresh_within, re…

### `search_claims` (~220 tokens)

Search claims

Search claims by text, subject, agent, status, authz_ref (the sha256 of an authorized plan) or depends_on (cd-1b: the parent claims that list a given claim id). Each item carries receipt_url, counts_as_verified and limits. Paginated: returns total, truncated and next_offset (limit default 20, max 100); pass offset to get the next page.

Input parameters:

- `agent` (string)
- `authz_ref` (string): az-1: sha256:<64 hex> of an authorized plan; returns the claims committed to it
- `depends_on` (string): cd-1b reverse lookup: one claim id; returns the public parent claims that list it in depends_on (who relies on this claim)
- `host` (string): fc-1: bare hostname filter matching subject or check URLs/hosts
- `limit` (integer)
- `offset` (integer)
- `q` (string)
- `status` (string)
- `subject` (string)

### `list_check_types` (~20 tokens)

List check types

Public check types the hosted service runs, with parameters.

### `suggest_checks` (~374 tokens)

Suggest checks for a claim

Turn a plain-language claim into proposed Countersign checks, deterministically (URLs, domains, PRs, shas, IPs, quoted text, repo paths; no LLM). Ranked by confidence and by how each recipe has held up in the ledger. Use ready_hosted_checks directly with submit_claim; fill `needs` params otherwise. The same extractor decides at submit time whether the checks test the statement. `independence` counts the independent evidence sources (is-1) the ready checks would have; when fewer than two, `second_source` proposes checks on a record the claimant does not write (add them yourself). `depth` (ed-1) says whether the ready checks assert content or only that the thing exists; when existence_only, `content_check` proposes content versions (fill `needs`). Package releases on npm or PyPI (rg-1) get a registry check the publisher does not write. URLs the statement says must not change ("without changing <url>", "<url> is unchanged") become prohibited_effect_preserved checks with role must_not_change (mnc-2); pass pin: true to fill body_sha256 now (vp-1: a page that changes between two reads gets no pin; a contains / json_fields check on its stable content is proposed instead). nb-1: when it finds must-not-change targets, nudges[] carries the exact pin_before_work call for them; make it BEFORE you start the work so the baseline reads before_work, not at_filing.

Input parameters:

- `pin` (boolean): mnc-2: for URLs the statement says must not change, read each body's sha256 now with the checker's own fetch (at most 3) so the prohibited_effect_preserved check is ready to submit
- `statement` (string, required)

### `pin_before_work` (~127 tokens)

Pin targets before the work

Pin before work (pb-1): call this BEFORE you start, with up to 3 URLs the work must not change. Each is read now (twice, vp-1) with the checker's own fetch and gets a signed pin_id and a ready must_not_change check (body_sha256, or contains / json_fields for a page that changes on every load). After the work, pass those checks unchanged in submit_claim's must_not_change; the receipt then says the baseline was read before the claim was filed, not supplied at filing.

Input parameters:

- `urls` (array, required)

### `get_track_record` (~123 tokens)

Get an agent's track record

Deterministic reputation computed from the public ledger (formula at /trust): score 0-100 with confidence, verified and refutation rates, honest retirements, unhandled decays, countersignatures, median time to fix, flags, and shown-not-scored per-agent counts (qualification_counts, evidence_independence_counts, evidence_depth_counts: how many public live claims only show the thing exists; baseline_counts: how many must-not-change baselines were pinned before the work). Omit agent to get the ranked table.

Input parameters:

- `agent` (string)

### `get_decay_index` (~68 tokens)

Get the claim decay index

Kaplan-Meier decay index (dx-1): how long claims of each check type, claim kind and host class stay true, with 95% log-log confidence intervals. Consumer: the recheck scheduler and an agent choosing how long to trust a claim. Display only, not a verdict.

### `get_reliance_prior` (~153 tokens)

Base rate a new claim is still true

Given a new claim's features (check_type, claim_kind, host_class, or checks plus an optional statement), the Kaplan-Meier base rate that such a claim is still true after N days (default 1, 7 and 30). Display only, verdict_input false. The statement and check URLs are not echoed.

Input parameters:

- `check_type` (string)
- `checks` (array)
- `claim_kind` (string)
- `days` (string): Comma-separated whole days, 0 to 365. Default 1,7,30
- `host_class` (string)
- `statement` (string): Used only to classify claim kind. Not stored and not returned.

### `get_digest` (~105 tokens)

Get a team digest

Team digest (dg-1), display only: for up to 25 agents, counts of their public claims by lifecycle state (verified, refuted, decayed, indeterminate_unobservable, pending_finality, withdrawn) and the claims newly refuted or newly decayed since `since` (default 24 hours ago), with receipt links and a ready Markdown block (markdown). Unknown agents get zero counts.

Input parameters:

- `agents` (array, required)
- `since` (string)

### `audit_ledger` (~57 tokens)

Audit the ledger

Re-verify the receipt hash chain, claim digests and runner signatures. Pass since (a checkpoint <seq>:<hash> from an earlier ok audit or an anchor) to verify only newer receipts.

Input parameters:

- `since` (string)

### `check_report_citations` (~131 tokens)

Check draft report citations (fc-1)

Check a draft status report (e.g. message to user) before sending: extracts all cited claim IDs (cs-.../csh-...) and bare hostnames/URLs, verifies each cited claim is counts_as_verified: true (and fresh if fresh_within is passed), and flags any host reported as live/fixed/deployed without a verified receipt.

Input parameters:

- `agent` (string): Optional agent name for resolving local claim IDs
- `fresh_within` (string): Optional freshness window like 24h or 1h
- `text` (string, required): Draft status message or report text

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-signalry-countersign/countersign#diagnostics

## Score history

- 2026-11-06: 66
- 2026-11-05: 66
- 2026-11-04: 65

## Common questions

### What is the Countersign by Signalry MCP server?

Countersign by Signalry is an MCP server listed in the public MCP registry as ai.signalry/countersign. Countersign by Signalry: re-runs the checks behind an AI agent's done claim; hash-chained receipts. This page covers its hosted endpoint (https://countersign.signalry.ai/mcp).

### Is the Countersign by Signalry MCP server safe to use?

Countersign by Signalry scores 66 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Countersign by Signalry MCP server expose?

Countersign by Signalry exposes 19 tools: submit_claim, file_deploy_claim, submit_deploy_claim, verify_claim, withdraw_claim, and 14 more. Their descriptions and schemas cost roughly 5,106 tokens of context every time the server is loaded.

### Does the Countersign by Signalry MCP server require authentication?

No. We connected to Countersign by Signalry without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Countersign by Signalry MCP server still maintained?

Countersign by Signalry is still listed as active in the MCP registry. We last reached this channel on 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Countersign by Signalry MCP server?

VerifyMCP ran 13 checks on Countersign by Signalry, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://countersign.signalry.ai/mcp
- Website: https://countersign.signalry.ai/start?ref=mcp-registry
- Changelog RSS feed: https://verifymcp.io/servers/ai-signalry-countersign/countersign.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-signalry-countersign/countersign/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-signalry-countersign/countersign.json
- HTML version of this page: https://verifymcp.io/servers/ai-signalry-countersign/countersign