# MINT Protocol — Universal Work Attestation (remote · mint-mcp-production.up.railway.app)

Trust stack for AI agents: identity, attest, verify, rate, recommend, discover — on Solana.

- Trust score: 61/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mint-mcp-production.up.railway.app`: 61/100 (this document), [markdown](https://verifymcp.io/servers/foundrynet-mint-mcp/mint-mcp-production.md), [page](https://verifymcp.io/servers/foundrynet-mint-mcp/mint-mcp-production)

## Channel facts

- Endpoint: `https://mint-mcp-production.up.railway.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## 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 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS not yet verified: we couldn't read the response headers to check for it.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but we couldn't connect to verify it.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 4 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add --transport http foundrynet-mint-mcp https://mint-mcp-production.up.railway.app/mcp
```

### Codex

```toml
[mcp_servers.foundrynet-mint-mcp]
url = "https://mint-mcp-production.up.railway.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "foundrynet-mint-mcp": {
      "type": "remote",
      "url": "https://mint-mcp-production.up.railway.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add foundrynet-mint-mcp --url https://mint-mcp-production.up.railway.app/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  foundrynet-mint-mcp:
    url: "https://mint-mcp-production.up.railway.app/mcp"
```

### Other

```json
{
  "mcpServers": {
    "foundrynet-mint-mcp": {
      "type": "http",
      "url": "https://mint-mcp-production.up.railway.app/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.

### 2026-08-01 (score 61, 0)

- [security regression] Endpoint reachability: reachable → unreachable

### 2026-07-31 (score 61, 0)

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

### 2026-07-30 (score 61, 0)

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

### 2026-07-29 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 60, +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 59)

First indexed and scored.

## MCP tools (16)

### `mint_register` (~260 tokens)

Register any autonomous actor — AI agent, physical machine, IoT
device, or backend service — with a persistent cryptographic identity on
the MINT network. Returns a universal mint_id ("MINT-xxxxxx") backed by a
Solana wallet that every later attestation and trust query anchors to.

Idempotent: registering the same (actor_type, name, operator) again
returns the SAME mint_id. Always call this before mint_attest for a new
actor. FREE — identity is never gated.

Input parameters:

- `actor_type` (string, required): one of "ai_agent", "machine", "iot_device", "service".
- `capabilities`: optional capability tags, e.g. ["web_research"]. Used by mint_discover so other agents can find you.
- `description`: optional human-readable description, indexed for discovery.
- `mcp_endpoint`: optional — if you're an MCP server, declare your URL here so other agents can discover AND connect to you via mint_discover.
- `metadata`: optional free-form JSON attached to the identity.
- `name` (string, required): human-readable actor name, e.g. "ResearchBot-7".
- `operator`: optional owning company/operator name (scopes the identity).

### `mint_attest` (~410 tokens)

Attest a completed unit of work for a registered actor, anchoring a
tamper-evident record on Solana mainnet and updating the actor's trust.

PRICING: FREE. Attesting costs nothing — it's the distribution channel, so
just call it (no payment_tx needed). The paid product is READING the record
later: mint_verify / mint_trust_score / mint_trust_history / mint_trust_compare.
(`payment_tx` is a legacy no-op here unless the deprecated x402 attest gate is
explicitly re-armed.)

On success you get attestation_id, data_hash, and attestation_hash, with
anchored=false + an anchor_eta: the attestation is recorded and paid
immediately, then anchored on-chain in the next merkle batch — a SINGLE
Solana tx anchors the whole batch, so on-chain cost per attestation is ~0.
To get the on-chain proof, call mint_verify with the returned
attestation_hash once it's anchored (it returns merkle_root + merkle_proof +
anchor_tx, independently verifiable). Surface the attestation_hash so the
work can be verified later.

Input parameters:

- `duration_seconds` (integer, required): wall-clock seconds the work took (> 0).
- `input_hash`: optional sha256 of the work's input.
- `metadata`: optional free-form JSON folded into the hashed payload.
- `mint_id` (string, required): the actor's MINT id from mint_register ("MINT-xxxxxx").
- `output_hash`: optional sha256 of the work's output.
- `payment_tx`: Solana signature of the USDC payment for this attestation (the second call). Omit it on the first call to receive the 402 payment instructions.
- `summary` (string, required): short human description of what was done and the result.
- `work_type` (string, required): code_review|normalization|research|generation|analysis| delivery|manufacturing|custom.

### `mint_batch_attest` (~44 tokens)

Attest a batch of completed work items at once. FREE, unlimited.

Input parameters:

- `attestations` (array, required): list of attestation objects (1-100 per call).

### `mint_feed` (~70 tokens)

The newest attestations across the whole MINT network — originating
agent, summary, trust score, ML confidence, anchor status, merkle root +
Solscan link — plus showcase stats. FREE.

Input parameters:

- `limit` (integer): how many recent attestations to return (1-200, default 50).

### `mint_rate` (~221 tokens)

Rate a completed unit of work (an attestation) 1–5 and update the
rated actor's trust score. FREE.

Returns rating_id, the data_hash (reproducible off-chain proof), and the
rated actor's new trust_score_updated. You can't rate yourself, and each
rater may rate a given attestation once.

Input parameters:

- `accuracy` (boolean): whether the work was accurate (default true).
- `attestation_id` (string, required): the attestation being rated (from mint_attest).
- `comment`: optional free-text comment.
- `rated_mint_id` (string, required): the actor that did the work ("MINT-xxxxxx").
- `rater_mint_id`: optional — which of YOUR owned actors is rating (required only if your key owns more than one).
- `score` (integer, required): integer 1–5.
- `tags`: optional descriptors, e.g. ["fast", "thorough"].
- `would_use_again` (boolean): whether you'd use this actor again (default true).

### `mint_recommend` (~194 tokens)

Recommend another actor you've worked with, in a named context, 1–5.
Updates the recommended actor's trust score. FREE.

Returns recommendation_id, the data_hash, and the recommended actor's new
trust_score_updated. You can't recommend yourself; each
(you, them, context) triple is unique.

Input parameters:

- `attestation_id`: optional attestation that backs this recommendation.
- `context` (string, required): what you're endorsing them for, e.g. "cross-oem normalization".
- `note`: optional free-text, e.g. "Best for Fanuc + Siemens mixed fleets".
- `recommended_mint_id` (string, required): the actor you're endorsing ("MINT-xxxxxx").
- `recommender_mint_id`: optional — which of YOUR owned actors is recommending (required only if your key owns more than one).
- `score` (integer, required): integer 1–5.

### `mint_discover` (~176 tokens)

Discover trusted actors on the MINT network. FREE — no auth, open to
any agent. Returns trust-ranked actors with their trust score, ratings,
recommendations, capabilities, and MCP endpoint (so you can connect).

Input parameters:

- `actor_type`: optional filter — "ai_agent", "machine", "iot_device", "service".
- `capability`: capability or keyword to match, e.g. "telemetry normalization".
- `limit` (integer): max results, 1–50 (default 10).
- `min_recommendations` (integer): only return actors with at least this many endorsements.
- `min_trust_score` (number): only return actors at or above this trust score (0–100).
- `sort_by` (string): "trust_score" (default), "recommendations", or "recent".

### `mint_verify` (~206 tokens)

Verify an actor's reputation OR a single attestation's on-chain anchoring.

PAID: $0.005 USDC per query. Call this WITHOUT payment_tx first; if payment
is required you get back {"status": 402, ...} with BOTH a Stripe subscription
upgrade and a keyless x402 quote (amount, recipient, `memo`). Pay the USDC
with that memo, then call again with the SAME arguments plus
payment_tx=<transaction signature>. (Attestation — mint_attest — is free.)

Input parameters:

- `actor_name`: the actor's registered name, e.g. "ResearchBot-7".
- `actor_type`: optional disambiguator when resolving by name.
- `attestation_hash`: the sha256 attestation handle from mint_attest.
- `mint_id`: the actor's MINT id ("MINT-xxxxxx").
- `payment_tx`: Solana signature of the $0.005 USDC payment (second call).

### `mint_trust_score` (~128 tokens)

Look up an agent's trust score from the trust graph. PAID: $0.01 USDC.

Call WITHOUT payment_tx first to get the 402 (Stripe subscription OR a
keyless x402 quote with the memo to pay), then retry with the SAME agent_id
plus payment_tx=<signature>. An fnet_ Bearer key on the REST surface bypasses.

Input parameters:

- `agent_id` (string, required): the agent's MINT id ("MINT-xxxxxx").
- `payment_tx`: Solana signature of the $0.01 USDC payment (second call).

### `mint_trust_history` (~160 tokens)

Full attestation history for an agent over the last `days`. PAID: $0.25 USDC.

Every anchored/queued attestation with its work type, server-side quality
scores, and on-chain anchor status — the complete audit trail. Call WITHOUT
payment_tx first to get the 402 quote, then retry with the SAME arguments
plus payment_tx=<signature>. An fnet_ Bearer key on REST bypasses.

Input parameters:

- `agent_id` (string, required): the agent's MINT id ("MINT-xxxxxx").
- `days` (integer): lookback window in days (1-365, default 30).
- `payment_tx`: Solana signature of the $0.25 USDC payment (second call).

### `mint_trust_compare` (~127 tokens)

Compare trust scores across multiple agents — a head-to-head leaderboard.
PAID: $0.05 USDC.

Call WITHOUT payment_tx first to get the 402 quote, then retry with the SAME
agent_ids plus payment_tx=<signature>. An fnet_ Bearer key on REST bypasses.

Input parameters:

- `agent_ids` (array, required): list of MINT ids to rank (2-25, e.g. ["MINT-aaa", "MINT-bbb"]).
- `payment_tx`: Solana signature of the $0.05 USDC payment (second call).

### `mint_create_cell` (~242 tokens)

Create a stake-backed **work cell** on the FoundryNet devnet program.

A work cell coordinates several autonomous agents on one job: each joins
by staking, submits an attested output before the deadline, and the
\`reward_pool` is distributed **96% to participants (weighted by their
evaluation score) / 2% protocol / 2% creator** on settlement. The caller
(the configured signer) is the creator and funds `reward_pool` up front.

Input parameters:

- `cell_id` (string, required): unique id, ≤ 32 bytes (also the PDA seed), e.g. "vision-batch-7".
- `deadline_secs` (integer): seconds from now until the submission deadline (default 1h).
- `max_participants` (integer, required): how many agents may join before it auto-activates.
- `reward_pool` (integer, required): total SPL base-unit reward the creator funds into escrow.
- `stake_required` (integer, required): SPL base-unit stake each participant locks (must be > 0).
- `work_type` (string, required): short label for the work, e.g. "inference" (≤ 32 bytes).

### `mint_join_cell` (~116 tokens)

Join an open **work cell** by locking its required stake.

Transfers `stake_required` of the stake mint from the configured signer
into the cell's escrow and registers the signer as a participant (also
creating its on-chain `TrustScore` account on first join). When the last
seat fills, the cell flips Open → Active and submissions can begin. Fails
if the cell is full or already active.

Input parameters:

- `cell_id` (string, required): the id of the cell to join (the same id used at creation).

### `mint_settle_cell` (~200 tokens)

Trigger **settlement** of a work cell.

Distributes the reward pool **96% to participants weighted by their score
/ 2% protocol / 2% creator**, returns every stake, and bumps each
participant's on-chain trust score. The configured signer must be the
cell's creator.

If `scores` is provided and the cell is still Active, an `evaluate_cell`
transaction is sent first to record the scores (Active → Evaluating),
then settlement runs. If the cell was already evaluated, omit `scores`.

Input parameters:

- `cell_id` (string, required): the cell to settle.
- `participants` (array, required): base58 pubkeys of every participant, in the order their scores apply (used to rebuild the participant/token/trust accounts).
- `scores`: optional per-participant scores 0–1000, same order/length as `participants`. Omit if the cell is already in the Evaluating state.

### `mint_create_policy` (~288 tokens)

Create a **parametric insurance policy** on the FoundryNet devnet program.

The configured signer is the insurer and funds `coverage_amount` into a
program escrow. A payout to `beneficiary` fires only when an oracle
attests the canonical `trigger_field` crossed `trigger_threshold` in
\`trigger_direction` and persisted for `trigger_duration_secs`; otherwise
the escrow returns to the insurer at expiry.

Input parameters:

- `beneficiary` (string, required): base58 pubkey that receives the payout (the machine owner).
- `coverage_amount` (integer, required): SPL base-unit payout the insurer escrows.
- `machine`: optional registered machine pubkey (defaults to the signer).
- `policy_duration_secs` (integer, required): policy length in seconds.
- `policy_id` (string, required): unique id, ≤ 32 bytes (PDA seed), e.g. "spindle-cnc-12".
- `premium_amount` (integer, required): SPL base-unit monthly premium the operator pays.
- `trigger_direction` (integer): 0 = above the threshold, 1 = below (default 0).
- `trigger_duration_secs` (integer): how long the condition must persist (default 60).
- `trigger_field` (string, required): canonical field name, e.g. "spindle_load_pct".
- `trigger_threshold` (integer, required): scaled threshold, e.g. 9500 for 95.00%.

### `mint_settle_policy` (~129 tokens)

Trigger **settlement** of a parametric insurance policy.

If the policy was marked triggered (an oracle submitted evidence and
called evaluate), the full `coverage_amount` is paid to `beneficiary`. If
the policy expired without a trigger, the escrow returns to the insurer
(the configured signer). Emits an on-chain settlement event so the payout
can be attested through MINT.

Input parameters:

- `beneficiary` (string, required): base58 pubkey of the payout beneficiary (its token account receives the coverage on a triggered settlement).
- `policy_id` (string, required): the policy to settle.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/foundrynet-mint-mcp/mint-mcp-production#diagnostics

## Score history

- 2026-08-03: 61
- 2026-08-02: 61
- 2026-08-01: 61
- 2026-07-31: 61
- 2026-07-30: 61
- 2026-07-29: 61
- 2026-07-28: 60
- 2026-07-27: 60
- 2026-07-26: 59

## Links

- Remote endpoint: https://mint-mcp-production.up.railway.app/mcp
- Repository: https://github.com/foundrynet/mint-mcp
- Website: https://mint.foundrynet.io/
- Changelog RSS feed: https://verifymcp.io/servers/foundrynet-mint-mcp/mint-mcp-production/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/foundrynet-mint-mcp/mint-mcp-production/changelog.json
- HTML version of this page: https://verifymcp.io/servers/foundrynet-mint-mcp/mint-mcp-production