# Countersign (remote · countersign.llpro.ai)

Signed AI checks. Free daily quota; credit keys from $10 at llpro.ai/pay/credit; x402 accepted.

- Trust score: 64/100 (medium)
- Change this week: +10
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `countersign.llpro.ai`: 64/100 (this document), [markdown](https://verifymcp.io/servers/ai-llpro-countersign-countersign/countersign-2.md), [page](https://verifymcp.io/servers/ai-llpro-countersign-countersign/countersign-2)

## Channel facts

- Endpoint: `https://countersign.llpro.ai/mcp?via=mcp-registry`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.3`

## 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 2026-11-21.

- **Endpoint Security**: 63/100
  - 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 check failed: the endpoint is reachable over plaintext HTTP.
  - 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**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1428 tokens (~204/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 7 days we've observed: 3 tool removals, 0 breaking changes, 0 auth/transport breaks, 1 additions.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 82% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 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 MCP server?

Countersign is a hosted endpoint at https://countersign.llpro.ai/mcp?via=mcp-registry, 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-llpro-countersign-countersign 'https://countersign.llpro.ai/mcp?via=mcp-registry'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-llpro-countersign-countersign": {
      "url": "https://countersign.llpro.ai/mcp?via=mcp-registry"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-llpro-countersign-countersign": {
      "type": "http",
      "url": "https://countersign.llpro.ai/mcp?via=mcp-registry"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-llpro-countersign-countersign]
url = "https://countersign.llpro.ai/mcp?via=mcp-registry"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-llpro-countersign-countersign": {
      "type": "remote",
      "url": "https://countersign.llpro.ai/mcp?via=mcp-registry",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-llpro-countersign-countersign --url 'https://countersign.llpro.ai/mcp?via=mcp-registry' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-llpro-countersign-countersign:
    url: "https://countersign.llpro.ai/mcp?via=mcp-registry"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-llpro-countersign-countersign": {
      "Transport": "http",
      "Url": "https://countersign.llpro.ai/mcp?via=mcp-registry"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-llpro-countersign-countersign -t streamable-http -u 'https://countersign.llpro.ai/mcp?via=mcp-registry'
```

### Other

```json
{
  "mcpServers": {
    "ai-llpro-countersign-countersign": {
      "type": "http",
      "url": "https://countersign.llpro.ai/mcp?via=mcp-registry"
    }
  }
}
```

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.

### 2026-11-21 (score 64, 0)

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

### 2026-11-20 (score 64, +4)

- [security regression] Stability: 0.17 → fail
- [security regression] A breaking change shipped without a version bump: still 1.0.0
- [security regression] Tool “launchpad.start” was removed
- [security regression] Tool “launchpad.progress” was removed
- [security regression] Tool “feedback.submit” was removed
- [security improvement] Authorization: unverified → partial
- [security] Tool “countersign_stamp” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 173 → 201
- [functional] Schema quality: good → excellent
- [functional] New tool “agent_readiness_audit”
- [cosmetic] Tool “countersign_stamp” changed its title: Check work and get a signed stamp
- [cosmetic] Tool “countersign_log” changed its title: Read the public stamp log
- [cosmetic] Tool “countersign_verify” changed its title: Verify a stamp
- [cosmetic] Tool “launchpad_start” changed its title: Start here: get a plan for a goal
- [cosmetic] Tool “launchpad_progress” changed its title: Report progress on a plan
- [cosmetic] Tool “feedback_submit” changed its title: Send feedback to LLPRO

### 2026-11-19 (score 60, +3)

- [security] Tool “countersign_stamp” rewrote its description, which is the text the model reads
- [functional improvement] MCP protocol: fail → pass
- [functional] MCP protocol version: 2025-03-26 → 2026-07-28

### 2026-11-17 (score 57, +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.

### 2026-11-16 (score 56, +1)

- [security regression] HTTPS: unverified → fail
- [security] Tool “countersign_log” rewrote its description, which is the text the model reads
- [security] Tool “countersign_verify” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 145 → 167
- [functional improvement] Tool coverage: 68% → 78%
- [cosmetic] “countersign_log” reworded the description of “after”
- [cosmetic] “countersign_log” reworded the description of “limit”
- [cosmetic] “countersign_verify” reworded the description of “id”
- [cosmetic] “countersign_verify” reworded the description of “output”

### 2026-11-15 (score 55, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-14 (score 54)

First indexed and scored.

## MCP tools (7)

### `countersign_stamp` (~353 tokens)

Check work and get a signed stamp

Use when you need a signed check, by code that did not make the work, of work you or another agent produced (a report, calculation, summary, filing draft or code) before relying on it or handing it on. Countersign re-computes arithmetic, looks up quotes and values in the cited sources, opens links and parses code, then returns a signed stamp (pass, fail or inconclusive) saying exactly what is wrong, with time and method. The stamp is kept in a public log. No AI model decides the result. It never checks work it produced. Free daily quota; credit keys from $1 at llpro.ai/pay/credit; x402 accepted. Send the key as Authorization: Bearer <llk_ key>. We charge only while this tool passes today's known-answer test; in testing it answers free.

Input parameters:

- `claims` (array): Optional explicit items: {type:'arithmetic', expression, claimed} or {type:'quote', source_url, quote} or {type:'value', source_url, value}
- `kind` (string)
- `language` (string): For code: python or json get a syntax check
- `output` (string, required): The work to check, as text (max 100000 chars). Equations written as '12 * 4 = 48' are re-computed.
- `private` (boolean): If true the public log shows only a hash of each finding's detail; you still get the full detail
- `producer` (object, required): Who made the work: {agent_id, model}. Required; used for the independence rule.
- `sources` (array): Optional cited sources: {url, quote?}

### `countersign_verify` (~171 tokens)

Verify a stamp

Confirm that a Countersign stamp someone shows you is real before you trust it. Use it when another agent hands you work with a stamp id: give the id, and optionally the exact work text to prove the stamp covers that text and nothing else. Returns the logged stamp, whether its signature is valid and, with the text, whether it matches. It checks the log's copy, not the copy you were shown: compare the returned verdict and output_sha256 with that copy. Free, read-only; it does not re-check the work itself (countersign_stamp does that).

Input parameters:

- `id` (string, required): Stamp id: the id field returned by countersign_stamp
- `output` (string): Optional: the exact work text the stamp should cover; its sha256 is compared with the stamp

### `countersign_log` (~134 tokens)

Read the public stamp log

Read the public, append-only log of Countersign stamps: entries after a sequence number, in order, plus the head hash, entry count and public key so you can check signatures yourself. Use it when you audit stamps in bulk, mirror the log, or want to see where a stamp sits in the chain. Free, read-only; private stamps show only a hash of each finding's detail.

Input parameters:

- `after` (integer): Return entries with a sequence number above this (default 0 = from the first entry)
- `limit` (integer): Entries per call, 1 to 200 (default 20)

### `agent_readiness_audit` (~313 tokens)

Use when you or your user want a site or a code repo ready for agent traffic. Send a domain (example.com) or a public GitHub repo (https://github.com/owner/repo). Returns a 0-100 readiness score and each item checked, found or missing, why it matters and how to fix it. Site: /llms.txt, A2A agent card, MCP server card or endpoint, a payment path for agents (HTTP 402 / x402), robots.txt rules for AI agents, sitemap, OpenAPI. Repo: llms.txt, AGENTS.md, MCP registry server.json, agent card, README connect section. Read-only GET requests (at most 12), public addresses only, nothing stored about the site, signed result. First audit each day free; then $0.10 an audit (prepaid credit key or x402), charged only while it passes today's known-answer test. Free daily quota; credit keys from $1 at llpro.ai/pay/credit; x402 accepted. Send the key as Authorization: Bearer <llk_ key>. We charge only while this tool passes today's known-answer test; in testing it answers free.

Input parameters:

- `domain` (string): A website to audit, e.g. example.com (a full https URL is accepted; only the host name is used).
- `repo` (string): Or a public GitHub repo: https://github.com/owner/repo (send domain OR repo, not both).

### `feedback_submit` (~206 tokens)

Send feedback to LLPRO

Tell LLPRO what failed, what was missing or what would improve this service. Read daily by the service owner and turned into a fix or an answer; shipped ideas are credited on https://llpro.ai/changelog and earn a contributor mark on Agent Record. Not for support requests that need a reply: write support@llpro.ai for those. Do not send secrets.

Input parameters:

- `credit` (boolean): Default true: credit your agent id on the changelog if the idea ships. Send false to opt out.
- `message` (string): Anything else, in your own words.
- `rating` (integer)
- `tool` (string): Which tool or endpoint this is about.
- `what_failed` (string): What did not work, and the call that failed (tool, arguments, what you expected).
- `what_missing` (string): What you needed and could not get.
- `what_would_improve` (string): One concrete change that would make this better.

### `launchpad_start` (~147 tokens)

Start here: get a plan for a goal

Stuck? Start here. Give your goal and any limits; get back a concrete plan (LLPRO tools first, then registries and the open web), the first task to run, and a token to report progress. Free. The goal is read for keywords only and is never stored. Anything that spends, signs, sends, shares, connects or deletes is marked as needing your owner's approval.

Input parameters:

- `agent_id` (string): A stable name for you. Used only to count return visits.
- `constraints` (object): Optional limits. They only ever make the plan stricter.
- `goal` (string, required): What you are trying to get done, in a sentence or two.

### `launchpad_progress` (~104 tokens)

Report progress on a plan

Report where you are on a Launchpad plan and get the next step, an on-track check and, if you are stuck, a way round. Needs the launch_id and token from launchpad.start.

Input parameters:

- `launch_id` (string, required)
- `reason` (string): Only with status stuck.
- `status` (string)
- `step` (string): A step id from your plan. Leave out to ask where you are.
- `token` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-llpro-countersign-countersign/countersign-2#diagnostics

## Score history

- 2026-11-21: 64
- 2026-11-20: 64
- 2026-11-19: 60
- 2026-11-18: 57
- 2026-11-17: 57
- 2026-11-16: 56
- 2026-11-15: 55
- 2026-11-14: 54

## Common questions

### What is the Countersign MCP server?

Countersign is an MCP server listed in the public MCP registry as ai.llpro.countersign/countersign. Signed AI checks. Free daily quota; credit keys from $10 at llpro.ai/pay/credit; x402 accepted. This page covers its hosted endpoint (https://countersign.llpro.ai/mcp?via=mcp-registry).

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

Countersign scores 64 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 MCP server expose?

Countersign exposes 7 tools: countersign_stamp, countersign_verify, countersign_log, agent_readiness_audit, feedback_submit, and 2 more. Their descriptions and schemas cost roughly 1,428 tokens of context every time the server is loaded.

### Does the Countersign MCP server require authentication?

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

### Is the Countersign MCP server still maintained?

Countersign is still listed as active in the MCP registry. We last reached this channel on 21 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 MCP server?

VerifyMCP ran 13 checks on Countersign, 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.llpro.ai/mcp?via=mcp-registry
- Website: https://countersign.llpro.ai/llms.txt
- Changelog RSS feed: https://verifymcp.io/servers/ai-llpro-countersign-countersign/countersign-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-llpro-countersign-countersign/countersign-2/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-llpro-countersign-countersign/countersign-2.json
- HTML version of this page: https://verifymcp.io/servers/ai-llpro-countersign-countersign/countersign-2
