# Proofable MCP (remote · mcp.proofable.me)

Give AI agents real access without giving up control through Proofable MCP.

- Trust score: 36/100 (low)
- Change this week: −39
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-07

## Components

- remote · `mcp.proofable.me`: 36/100 (this document), [markdown](https://verifymcp.io/servers/proofable-mcp/mcp.md), [page](https://verifymcp.io/servers/proofable-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.proofable.me/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.5`

## 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 2026-10-07.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 0/100
  - Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
- **Schema Quality & AI Usability**: 0/100
  - Schema blocked by authentication: the endpoint requires auth we don't have to read it.
- **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 blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Tool Safety**: 0/100
  - Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Capabilities**: 0/100
  - Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

**Unverified: 6 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

### How do I install the Proofable MCP server?

Proofable MCP is a hosted endpoint at https://mcp.proofable.me/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 proofable-mcp 'https://mcp.proofable.me/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "proofable-mcp": {
      "url": "https://mcp.proofable.me/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "proofable-mcp": {
      "type": "http",
      "url": "https://mcp.proofable.me/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.proofable-mcp]
url = "https://mcp.proofable.me/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add proofable-mcp --url 'https://mcp.proofable.me/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  proofable-mcp:
    url: "https://mcp.proofable.me/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "proofable-mcp": {
      "Transport": "http",
      "Url": "https://mcp.proofable.me/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add proofable-mcp -t streamable-http -u 'https://mcp.proofable.me/mcp'
```

### Other

```json
{
  "mcpServers": {
    "proofable-mcp": {
      "type": "http",
      "url": "https://mcp.proofable.me/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.

### 2026-10-07 (score 36, −40)

- [security regression] Endpoint reachability: reachable → behind authorisation
- [security regression] Stability: fail → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → unverified
- [security] Authorization: The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-10-01 (score 76, +1)

- [security regression] Stability: 0.03 → fail
- [security regression] A breaking change shipped without a version bump: still 0.1.3
- [security regression] Tool “proofable_agent_create” was removed
- [security regression] Tool “proofable_agent_link” was removed
- [security regression] Tool “proofable_agent_mount” was removed
- [security regression] Tool “proofable_proofs_get” was removed
- [security regression] Tool “proofable_proofs_update” was removed
- [security regression] Tool “proofable_secret_create” was removed
- [security regression] Tool “proofable_secret_list” was removed
- [security regression] Tool “proofable_secret_revoke” was removed
- [security regression] Tool “proofable_verify” was removed
- [functional improvement] Schema quality: 3155 → 961
- [functional] Destructive annotations: 100 → pass

### 2026-09-30 (score 75, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-29 (score 75, +39)

- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 97
- [functional] First check of Schema quality: excellent
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: 100
- [functional] First check of Tool coverage: 100

### 2026-09-28 (score 36, 0)

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

### 2026-09-25 (score 36, 0)

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

### 2026-09-11 (score 36)

First indexed and scored.

## MCP tools (4)

### `proofable_context` (~43 tokens)

Start here. Returns the signed-in profile, available verifiers, and the recommended workflow in one call. Handles signed-in and offline modes, no separate profile tool needed.

Output parameters:

- `agentsError` (string)
- `agentsStatus` (string)
- `authenticated` (boolean)
- `contextIndex`
- `error` (string)
- `message` (string)
- `profile` (object)
- `recommendedWorkflow`
- `status`
- `verifierSummary` (array)

### `proofable_verifiers_catalog` (~39 tokens)

Full verifier catalog: supported networks and required inputs. Use this when a verifier needs schema details beyond the compact verifierSummary in proofable_context.

Output parameters:

- `error` (string)
- `message` (string)
- `status`
- `verifiers` (array)

### `proofable_proofs_check` (~176 tokens)

Does this wallet already have the required proofs? Returns pass or fail, not records. To read proofs, use proofable_proofs_get. Omit the wallet when signed in.

Input parameters:

- `gateId` (string): Optional hosted gate or listing id. Signed-in owners still get eligible + matchedCount only.
- `handle` (string): Optional handle filter for handle-based verifiers.
- `minCount` (number): Minimum number of matching proofs. Default 1.
- `namespace` (string): Optional namespace filter for handle checks.
- `requireAll` (boolean): Require all listed verifiers. Default false accepts any one.
- `verifiers` (array, required): Verifier IDs from proofable_verifiers_catalog.
- `wallet` (string): Wallet or DID to verify. Omit when signed in to use the current account.

Output parameters:

- `eligible` (boolean)
- `error` (string)
- `matchedCount` (number)
- `message` (string)
- `satisfied` (boolean)
- `status`
- `success` (boolean)
- `unknownVerifiers` (array)

### `proofable_verify_or_guide` (~177 tokens)

Reuse a qualifying portable proof or return the one next step needed to finish verification. Omit the wallet when signed in. Signed-in ownership proofs continue with proofable_verify. A hosted link is returned only for an outside login, payment, or different account.

Input parameters:

- `chain` (string): Optional network hint. Omit when Proofable can infer it from the wallet format.
- `data` (object): Inputs for the selected verifiers. Used only when a new Proof is needed.
- `options` (object): Optional verification options
- `requireAll` (boolean): Require all listed verifiers. Default false accepts any one.
- `verifierIds` (array, required): Verifier IDs from proofable_verifiers_catalog.
- `walletAddress` (string): Wallet or DID. Omit when signed in to use the current account.

Output parameters:

- `action` (string)
- `eligible` (boolean)
- `error` (string)
- `hostedVerifyUrl` (string)
- `matchedCount` (number)
- `message` (string)
- `proofs` (array)
- `status`
- `success` (boolean)

## Diagnostics

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

## Score history

- 2026-10-07: 36
- 2026-10-04: 76
- 2026-10-03: 76
- 2026-10-02: 76
- 2026-10-01: 76
- 2026-09-30: 75
- 2026-09-29: 75
- 2026-09-28: 36
- 2026-09-27: 36
- 2026-09-26: 36
- 2026-09-25: 36
- 2026-09-24: 36
- 2026-09-23: 36
- 2026-09-22: 36
- 2026-09-21: 36
- 2026-09-20: 36
- 2026-09-19: 36
- 2026-09-18: 36
- 2026-09-17: 36
- 2026-09-16: 36
- 2026-09-15: 36
- 2026-09-14: 36
- 2026-09-13: 36
- 2026-09-12: 36
- 2026-09-11: 36

## Common questions

### What is the Proofable MCP server?

Proofable MCP is listed in the public MCP registry as io.github.proofable/mcp. Give AI agents real access without giving up control through Proofable MCP. This page covers its hosted endpoint (https://mcp.proofable.me/mcp).

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

Proofable MCP scores 36 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 Proofable MCP server expose?

Proofable MCP exposes 4 tools: proofable_context, proofable_verifiers_catalog, proofable_proofs_check, proofable_verify_or_guide. Their descriptions and schemas cost roughly 435 tokens of context every time the server is loaded.

### Does the Proofable MCP server require authentication?

Yes. Proofable MCP asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Proofable MCP server still maintained?

Proofable MCP is still listed as active in the MCP registry. We last reached this channel on 7 October 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://mcp.proofable.me/mcp
- Repository: https://github.com/proofable/mcp
- Website: https://docs.proofable.me/mcp/setup
- Changelog RSS feed: https://verifymcp.io/servers/proofable-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/proofable-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/proofable-mcp/mcp