Skip to main content
ClaudeWave

MCP server whose only tools verify and decode Forestrie receipts. No backend, no account, no key, no network.

MCP ServersOfficial Registry0 stars0 forksTypeScriptMITUpdated today
ClaudeWave Trust Score
87/100
Trusted
Passed
  • Open-source license (MIT)
  • Actively maintained (<30d)
  • Clear description
  • Documented (README)
Last scanned: 9/14/2026
Install in Claude Code / Claude Desktop
Method: NPX · @forestrie/mcp-verify
Claude Code CLI
claude mcp add mcp-verify -- npx -y @forestrie/mcp-verify
claude_desktop_config.json (Claude Desktop)
{
  "mcpServers": {
    "mcp-verify": {
      "command": "npx",
      "args": ["-y", "@forestrie/mcp-verify"]
    }
  }
}
1. Run the command above in your terminal (Claude Code), or paste the JSON config into claude_desktop_config.json (Claude Desktop).
2. Replace any <placeholder> values with your API keys or paths.
3. Restart Claude. The MCP server and its tools appear automatically.
Use cases

MCP Servers overview

# @forestrie/mcp-verify

An MCP server whose only tools verify and decode Forestrie receipts.
**No backend, no account, no key, no network.**

```json
{
  "mcpServers": {
    "forestrie-verify": {
      "command": "npx",
      "args": ["-y", "@forestrie/mcp-verify"]
    }
  }
}
```

```
npx -y @forestrie/mcp-verify demo
```

## Why

Agents act on statements they did not witness being made: a quote, an
approval, a tool result, another agent's output. Usually the record of what
was said is kept by the party that said it, so nobody downstream can ask
"did you really say that, and did you say it to everyone?"

A Forestrie receipt is a proof that a statement was sealed into an
append-only transparency log. This package checks that proof against a trust
root you hold, in your own process, without contacting Forestrie. With the
right root it also answers the harder question: whether the log you were
shown is the log everyone else was shown. What transparency adds, where it
stops, and what a receipt contains: [TRANSPARENCY.md](TRANSPARENCY.md).

## What it proves

| Tool                   | Reference verb                    | What it answers                                                              |
| ---------------------- | --------------------------------- | ---------------------------------------------------------------------------- |
| `verify_receipt`       | `forestrie verify`                | Were these exact payload bytes sequenced at this entry id?                   |
| `verify_grant_receipt` | `forestrie verify-grant`          | Was this grant admitted to this log — i.e. was the signer entitled to write? |
| `verify_self`          | `forestrie verify`                | Does this package's own release receipt vouch for the bytes it ships?        |
| `decode_receipt`       | `forestrie decode-receipt --json` | What is actually in this receipt? (Renders the CBOR only. Verifies nothing.) |

Every tool is annotated `readOnlyHint: true, openWorldHint: false`. That is
not decoration: it is the machine-readable form of _"this tool touches
nothing"_, and an agent can see it without running anything.

## Trust roots

You do not ask for "verification". You say which root you trust, and the
result says what that root can see:

| Root                | What you supply                                             |
| ------------------- | ----------------------------------------------------------- |
| `genesis`           | the forest's genesis document, captured when you registered |
| `known-log-key`     | a log owner key you hold out of band                        |
| `known-accumulator` | a snapshot of the log's peaks, from a chain read            |
| `checkpoint-chain`  | a retained chain of `.sth` checkpoints                      |

The roots are not ordered by strength. The first two check the operator's signature
locally and cannot see a split view. The last two match the peak against an
accumulator the operator does not control, and can. Every result answers
four questions, **sealing**, **split-view**, **append-authority** and
**attribution**, each `ok`, `failed`, or `not_answered_by_this_root`. The
last is a real answer and must reach the user; a client that renders only
`ok` is using this tool wrong.

When each root is the effective choice, why a genesis document fetched at
check time is weaker than one kept from registration, what a signature root
cannot distinguish, and the demo transcript:
[docs/trust-roots.md](docs/trust-roots.md).

## Not a trust circle

> The root of trust is the univocity checkpoint the receipt chains to, not the
> package; the package supplies the arithmetic, which any independent
> implementation can re-run.

Which is why this repo goes to some trouble to make that re-running possible:

- **A differential test** against the published `@forestrie/forestrie-cli`
  npm package, pinned at an exact version. For every tamper variant under both
  signature roots, our `ok`, `stage`, `reason` and `stages[]` must equal the
  reference's byte for byte. Currently 18 tests, zero disagreements. See
  [docs/differential-test.md](docs/differential-test.md).
- **Frozen conformance vectors**, sha256-pinned to their manifest, shipped
  inside the tarball. See [fixtures/PROVENANCE.md](fixtures/PROVENANCE.md).
- **`files` includes `src`.** The package that asks you to trust its
  arithmetic ships the arithmetic.
- **Exact, provenance-attested dependencies** — no bundling, so
  `npm ls` and `npm audit signatures` both see the real graph. Bundling would
  hide `@forestrie/receipt-verify`'s own SLSA attestation behind ours.

The verification itself is `@forestrie/receipt-verify@1.0.0`, which is
published, MIT, and SLSA-attested independently of this package.
`decode_receipt`'s rendering stays a local implementation — over the same
published packages, against the same public
[label registry](https://github.com/forestrie/protocol/blob/main/spec/label-registry.md) —
rather than a dependency on `@forestrie/forestrie-cli`, whose published
decoder is otherwise a drop-in. Delegating to it has been tried twice and
reverted twice: the two label tables still name some codepoints with
different text, and that text is output the tool prints, so adopting it is a
deliberate change to what you see rather than a dependency bump. The
consolation is that it keeps the differential test's decode comparison
honest — two independent renderers that agree, rather than one compared with
itself. See [docs/dependency-surface.md](docs/dependency-surface.md).

At release time, this package also registers its own provenance in a
Forestrie log and ships the receipt inside the tarball — two independent
trust roots, npm's SLSA provenance and a Forestrie receipt, rather than one
circular one. See [docs/self-registration.md](docs/self-registration.md).

## Registry

Once phase 3 lands, this server is listed as `dev.forestrie/verify` in the
[official MCP registry](https://registry.modelcontextprotocol.io).

## Development

```
mise install           # node 22.14.0, pnpm 10.6.5
pnpm install
pnpm test              # browser-safe gate + encoding-copy gate + server.json gate + unit tests
pnpm test:differential # npm-installs the pinned forestrie CLI version
pnpm build
```

Conventions, invariants and the release checklist: [AGENTS.md](AGENTS.md).
Dependency surface and install weight:
[docs/dependency-surface.md](docs/dependency-surface.md).

## Licence

MIT.

What people ask about mcp-verify

What is forestrie/mcp-verify?

+

forestrie/mcp-verify is mcp servers for the Claude AI ecosystem. MCP server whose only tools verify and decode Forestrie receipts. No backend, no account, no key, no network. It has 0 GitHub stars and its last recorded update is dated 2026-09-13.

How do I install mcp-verify?

+

You can install mcp-verify by cloning the repository (https://github.com/forestrie/mcp-verify) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is forestrie/mcp-verify safe to use?

+

Our security agent has analyzed forestrie/mcp-verify and assigned a Trust Score of 87/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.

Who maintains forestrie/mcp-verify?

+

forestrie/mcp-verify is maintained by forestrie. The last recorded GitHub activity is dated 2026-09-13, with 0 open issues.

Are there alternatives to mcp-verify?

+

Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.

Deploy mcp-verify to your cloud

Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.

Maintain this repo? Add a badge to your README

Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.

Featured on ClaudeWave: forestrie/mcp-verify
[![Featured on ClaudeWave](https://claudewave.com/api/badge/forestrie-mcp-verify)](https://claudewave.com/repo/forestrie-mcp-verify)
<a href="https://claudewave.com/repo/forestrie-mcp-verify"><img src="https://claudewave.com/api/badge/forestrie-mcp-verify" alt="Featured on ClaudeWave: forestrie/mcp-verify" width="320" height="64" /></a>

More MCP Servers

mcp-verify alternatives