# RunOnProof — Payment Decision and Agent ID (remote · api.runonproof.com)

Free agent identity and signed US supplier-payment decisions. Inspect first; verify portable proof.

- Trust score: 73/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-27

## Components

- remote · `api.runonproof.com`: 73/100 (this document), [markdown](https://verifymcp.io/servers/runonproof-cdo/v1-agent-mcp-2.md), [page](https://verifymcp.io/servers/runonproof-cdo/v1-agent-mcp-2)

## Channel facts

- Endpoint: `https://api.runonproof.com/v1/agent/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `3.1.2`

## 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 2026-09-27.

- **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. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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**: 75/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1070 tokens (~48/item across 22 items; 16 tools + 6 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 15/100
  - Stability check failed: schema churn in the 30 days we've observed: 38 tool removals, 0 breaking changes, 0 auth/transport breaks, 9 additions.
- **Tool Coverage**: 73/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 5% of tool parameters carry a description.
  - Structured output schemas are declared (6% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the RunOnProof — Payment Decision and Agent ID MCP server?

RunOnProof — Payment Decision and Agent ID is a hosted endpoint at https://api.runonproof.com/v1/agent/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 runonproof-cdo 'https://api.runonproof.com/v1/agent/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "runonproof-cdo": {
      "url": "https://api.runonproof.com/v1/agent/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "runonproof-cdo": {
      "type": "http",
      "url": "https://api.runonproof.com/v1/agent/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.runonproof-cdo]
url = "https://api.runonproof.com/v1/agent/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "runonproof-cdo": {
      "type": "remote",
      "url": "https://api.runonproof.com/v1/agent/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add runonproof-cdo --url 'https://api.runonproof.com/v1/agent/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  runonproof-cdo:
    url: "https://api.runonproof.com/v1/agent/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "runonproof-cdo": {
      "Transport": "http",
      "Url": "https://api.runonproof.com/v1/agent/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add runonproof-cdo -t streamable-http -u 'https://api.runonproof.com/v1/agent/mcp'
```

### Other

```json
{
  "mcpServers": {
    "runonproof-cdo": {
      "type": "http",
      "url": "https://api.runonproof.com/v1/agent/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.

### 2026-09-25 (score 73, 0)

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

### 2026-09-21 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 5 to 9.

### 2026-09-19 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 2.

### 2026-09-10 (score 71, −1)

- [cosmetic] “verify_agent_signature” added an optional parameter “invitation_ref”

### 2026-09-09 (score 72, +1)

- [functional regression] Schema quality: 654 → 1062
- [functional regression] Tool coverage: 13% → 6%
- [functional] New tool “get_agent_public_profile”
- [functional] New tool “get_agent_identity_status”
- [functional] New tool “get_agent_identity_jwks”
- [functional] New tool “get_agent_id_bootstrap”
- [functional] New tool “export_agent_identity”
- [functional] New tool “create_agent_identity_challenge”
- [functional] New tool “verify_agent_signature”
- [functional] New tool “prove_agent_key_control”

### 2026-09-06 (score 71, 0)

- [cosmetic] “release_payment_to_supplier” added an optional parameter “decision_fee_payer”

### 2026-09-05 (score 71, −6)

- [security regression] Stability: 0.37 → fail
- [security regression] A breaking change shipped without a version bump: still 3.0.0
- [security regression] Tool “screen_restricted_party” was removed
- [security regression] Tool “build_uk_company_capability_passport” was removed
- [security regression] Tool “company_check” was removed
- [security regression] Tool “continue_vendor” was removed
- [security regression] Tool “continue_vendor_authorization” was removed
- [security regression] Tool “counterfactual” was removed
- [security regression] Tool “decide” was removed
- [security regression] Tool “detect_uk_company_material_change” was removed
- [security regression] Tool “issue_company_passport” was removed
- [security regression] Tool “match_uk_business_payee” was removed
- [security regression] Tool “match_uk_invoice_to_company” was removed
- [security regression] Tool “refresh” was removed
- [security regression] Tool “refresh_company_passport” was removed
- [security regression] Tool “resolve_legal_entity” was removed
- [security regression] Tool “resolve_uk_legal_entity” was removed
- [security regression] Tool “run_uk_company_check” was removed
- [security regression] Tool “run_uk_payment_authorization” was removed
- [security regression] Tool “run_uk_supplier_approval” was removed
- [security regression] Tool “run_uk_vendor_change_continuous_authorization” was removed
- [security regression] Tool “screen_restricted_business_party” was removed
- [security regression] Tool “validate_uk_business_document” was removed
- [security regression] Tool “verify_company_passport” was removed
- [security regression] Tool “verify_company_status” was removed
- [security regression] Tool “verify_invoice_payee” was removed
- [security regression] Tool “verify_uk_bank_account_ownership” was removed
- [security regression] Tool “verify_uk_beneficial_ownership_control” was removed
- [security regression] Tool “verify_uk_business_licence” was removed
- [security regression] Tool “verify_uk_company_status” was removed
- [security regression] Tool “verify_uk_invoice_and_payee” was removed
- [security regression] Tool “verify_uk_tax_registration” was removed
- [security regression] Tool “approve_supplier” was removed
- [security regression] Tool “approve_uk_supplier” was removed
- [security regression] Tool “assess_uk_invoice_authenticity_duplication” was removed
- [security regression] Tool “assess_uk_source_evidence_freshness” was removed
- [security regression] Tool “authorize_payment” was removed
- [security regression] Tool “authorize_uk_business_payment” was removed
- [security regression] Tool “authorize_uk_vendor_payment_detail_change” was removed
- [security regression] Tool “authorize_vendor_payment_detail_change” was removed
- [security] Tool “get_agent_first_portfolio” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 52% → 13%
- [functional regression] Tool coverage: 30% → 6%
- [functional improvement] Schema quality: 64 → 44

### 2026-09-04 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (16)

### `preflight` (~41 tokens)

Free: estimate resolvability, coverage, confidence and price for a CNPJ before paying.

Input parameters:

- `cnpj` (string, required): Brazilian CNPJ (14 digits)

### `capabilities` (~15 tokens)

Free: list all capabilities and prices.

### `verify_receipt` (~24 tokens)

Free: verify a signed decision receipt.

Input parameters:

- `receipt` (object, required)

### `verify_passport` (~24 tokens)

Free: verify a signed decision passport.

Input parameters:

- `passport` (object, required)

### `quote` (~21 tokens)

Free: quote for a capability.

Input parameters:

- `capability` (string, required)

### `release_payment_to_supplier` (~301 tokens)

Paid RunOnProof Payment Decision: one US FEDERAL_ONLY release-payment decision for 0.79 USDC on Base, with signed BuyerPaymentMandate, signed Proof Capsule and deterministic replay. RunOnProof does not execute supplier payment.

Input parameters:

- `amount` (string, required)
- `buyer` (object, required)
- `buyer_mandate` (object, required): Signed BuyerPaymentMandate bound to this request digest, buyer, agent, supplier, payee, limits and validity window.
- `correlation` (object, required)
- `coverage` (required)
- `coverage_requirements` (object, required)
- `currency` (string, required)
- `decision_fee_payer` (string): Decision fee wallet authorized by the signed request and buyer mandate; required for commercial x402 purchases.
- `disclosure` (object, required)
- `economic_purpose` (string, required)
- `evidence_references` (array, required)
- `exposure_valuation_basis` (string, required)
- `freshness_requirements` (object, required)
- `idempotency_key` (string, required)
- `intent` (required)
- `invoice` (object, required)
- `jurisdiction` (required)
- `payee` (object, required)
- `payment_destination` (object, required)
- `payment_exposure_usdc_equivalent_atomic` (string, required)
- `payment_instruction_digest` (string, required)
- `requesting_agent` (object, required)
- `risk_policy` (object, required)
- `schema_version` (required)
- `supplier` (object, required)

Output parameters:

- `billing` (object)
- `checks_executed` (array)
- `checks_waived` (array)
- `conditions` (array)
- `coverage` (object)
- `decision`
- `decision_cost` (object)
- `decision_id` (string)
- `decision_request_id` (string)
- `delivery` (object)
- `economic_risk` (object)
- `evidence_bundle` (object)
- `freshness` (object)
- `machine_action`
- `payment_executed`
- `policy` (object)
- `product`
- `product_version`
- `proof_capsule` (object)
- `reason_codes` (array)
- `remediation` (array)
- `replay` (object)
- `request_digest` (string)
- `request_id` (string)
- `risk_signals` (array)
- `schema_version`
- `uncertainty` (object)
- `valid_as_of` (string)
- `valid_until` (string)

### `resolve_agent_intent` (~63 tokens)

Free: select by canonical intent, brandless problem state or plain-language problem query, including honest negative selection; no source call, charge or settlement.

Input parameters:

- `intent_id` (string)
- `problem_state` (string)
- `query` (string)

### `get_agent_first_portfolio` (~26 tokens)

Free: return 1 commercial solution and 1 exact x402 resource.

### `get_agent_id_bootstrap` (~32 tokens)

Resolve the free RunOnProof Agent ID contract, exact next request, local-key rules and supported interfaces.

### `create_agent_identity_challenge` (~144 tokens)

Issue a free challenge for Agent ID enrollment or key lifecycle. Generate and retain private keys locally; this tool never accepts them.

Input parameters:

- `agent_id` (string)
- `authorizing_key_id` (string)
- `context` (object, required)
- `delegation_limits` (object)
- `delegation_scope` (array)
- `idempotency_key` (string, required)
- `new_public_key` (object)
- `operational_public_key` (object)
- `purpose` (required)
- `recovery_public_key` (object)
- `subagent_public_key` (object)
- `target_key_id` (string)
- `target_role`

### `prove_agent_key_control` (~44 tokens)

Submit detached local proofs and atomically consume an Agent ID challenge. No private key is accepted.

Input parameters:

- `challenge_id` (string, required)
- `proof` (object, required)

### `get_agent_public_profile` (~36 tokens)

Resolve one opaque Agent ID to a minimized key lifecycle; no directory or enumeration is provided.

Input parameters:

- `agent_id` (string, required)

### `get_agent_identity_status` (~30 tokens)

Resolve current Agent ID and key status with explicit freshness semantics.

Input parameters:

- `agent_id` (string, required)

### `get_agent_identity_jwks` (~38 tokens)

Resolve RFC 8037 public verification keys for one opaque Agent ID without enumerating identities.

Input parameters:

- `agent_id` (string, required)

### `export_agent_identity` (~36 tokens)

Export a portable public identity bundle for offline cryptographic verification with an explicit status-as-of limitation.

Input parameters:

- `agent_id` (string, required)

### `verify_agent_signature` (~56 tokens)

Verify cryptography, payload/context integrity, lifecycle interval, replay and temporal assurance for free.

Input parameters:

- `context` (object, required)
- `envelope` (object, required)
- `invitation_ref` (string)
- `payload` (object, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/runonproof-cdo/v1-agent-mcp-2#diagnostics

## Score history

- 2026-09-27: 73
- 2026-09-26: 73
- 2026-09-25: 73
- 2026-09-24: 73
- 2026-09-23: 73
- 2026-09-22: 73
- 2026-09-21: 73
- 2026-09-20: 72
- 2026-09-19: 72
- 2026-09-18: 71
- 2026-09-17: 71
- 2026-09-16: 71
- 2026-09-15: 71
- 2026-09-14: 71
- 2026-09-13: 71
- 2026-09-12: 71
- 2026-09-11: 71
- 2026-09-10: 71
- 2026-09-09: 72
- 2026-09-08: 71
- 2026-09-07: 71
- 2026-09-06: 71
- 2026-09-05: 71
- 2026-09-04: 77
- 2026-09-03: 76
- 2026-09-02: 76
- 2026-09-01: 75
- 2026-08-31: 75
- 2026-08-30: 75
- 2026-08-29: 74

## Common questions

### What is the RunOnProof — Payment Decision and Agent ID MCP server?

RunOnProof — Payment Decision and Agent ID is an MCP server listed in the public MCP registry as io.github.runonproof/cdo. Free agent identity and signed US supplier-payment decisions. Inspect first; verify portable proof. This page covers its hosted endpoint (https://api.runonproof.com/v1/agent/mcp).

### Is the RunOnProof — Payment Decision and Agent ID MCP server safe to use?

RunOnProof — Payment Decision and Agent ID scores 73 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 RunOnProof — Payment Decision and Agent ID MCP server expose?

RunOnProof — Payment Decision and Agent ID exposes 16 tools: preflight, capabilities, verify_receipt, verify_passport, quote, and 11 more. Their descriptions and schemas cost roughly 931 tokens of context every time the server is loaded.

### Does the RunOnProof — Payment Decision and Agent ID MCP server require authentication?

No. We connected to RunOnProof — Payment Decision and Agent ID without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the RunOnProof — Payment Decision and Agent ID MCP server still maintained?

RunOnProof — Payment Decision and Agent ID is still listed as active in the MCP registry. We last reached this channel on 27 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.runonproof.com/v1/agent/mcp
- Repository: https://github.com/runonproof/cdo
- Website: https://api.runonproof.com/v1/channels/mcp-registry/readme
- Changelog RSS feed: https://verifymcp.io/servers/runonproof-cdo/v1-agent-mcp-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/runonproof-cdo/v1-agent-mcp-2.json
- HTML version of this page: https://verifymcp.io/servers/runonproof-cdo/v1-agent-mcp-2