# BRYDGE (npm · brydge-mcp)

Checks whether an agent's actions actually happened, against the destination's own records.

- Trust score: 71/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-27

## Components

- npm · `brydge-mcp`: 71/100 (this document), [markdown](https://verifymcp.io/servers/com-brydge-ai-brydge/brydge-mcp.md), [page](https://verifymcp.io/servers/com-brydge-ai-brydge/brydge-mcp)

## Channel facts

- Registry: `npm`
- Package: `brydge-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 3 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 789 tokens (~157/item across 5 items; 5 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 not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% 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 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 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).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

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

BRYDGE runs locally as an npm package, launched with npx -y brydge-mcp. 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 com-brydge-ai-brydge -- npx -y brydge-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "com-brydge-ai-brydge": {
      "command": "npx",
      "args": [
        "-y",
        "brydge-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-brydge-ai-brydge": {
      "command": "npx",
      "args": [
        "-y",
        "brydge-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-brydge-ai-brydge -- npx -y brydge-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-brydge-ai-brydge": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "brydge-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-brydge-ai-brydge --command npx --arg -y --arg brydge-mcp
```

### Hermes

```yaml
mcp_servers:
  com-brydge-ai-brydge:
    command: "npx"
    args: ["-y", "brydge-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-brydge-ai-brydge": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "brydge-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-brydge-ai-brydge -t stdio -c npx -a -y brydge-mcp
```

### Other

```json
{
  "mcpServers": {
    "com-brydge-ai-brydge": {
      "command": "npx",
      "args": [
        "-y",
        "brydge-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-09-27 (score 71, +11)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 1.00

### 2026-09-26 (score 60)

First indexed and scored.

## MCP tools (5)

### `brydge_supervise` (~219 tokens)

Ask BRYDGE before acting

Ask BRYDGE whether you may take an action, before you take it. ALLOWED returns an authorization id: carry the action out and write that id into the record it creates, where the destination keeps it (for a Stripe refund: metadata.brydge_authorization). ESCALATED means a person decides: do not carry it out.

Input parameters:

- `action` (string, required): The kind of work, as it is set up in BRYDGE, such as refund.
- `facts` (object): What BRYDGE's rules judge the action by, such as {"amount": 4200}. BRYDGE compares a fact named amount with the amount in the destination's record, so give it in the same units.
- `idempotency_key` (string, required): A name for this one intended action, such as refund:ch_123. Send the same value if you retry the same action; never reuse it for a different one.
- `target` (string, required): What the work acts on: the charge, order or ticket id.

Output parameters:

- `authorization` (string)
- `because` (string)
- `decision` (string)
- `replayed` (boolean)
- `unobserved` (array)

### `brydge_report_outcome` (~138 tokens)

Report what happened

Tell BRYDGE what you believe happened after you carried out an allowed action. BRYDGE keeps your report beside what it finds in the destination's records; the report never changes the finding.

Input parameters:

- `authorization` (string, required): The authorization id brydge_supervise returned for the action.
- `outcome` (string, required): SUCCEEDED: it was carried out and did what it was meant to. FAILED: the destination refused it or errored. REVERSED: it happened and was undone. CORRECTED: it happened and had to be fixed afterwards.
- `said` (string): What the destination said, in its own words.

Output parameters:

- `authorization` (string)
- `recorded` (string)

### `brydge_verify` (~122 tokens)

Check the work actually happened

Check whether an action actually happened. BRYDGE reads the destination system's own records now, with its own credential, and compares them with what it permitted. Only VERIFIED means it happened as permitted; FAILED, MISMATCH, UNKNOWN (BRYDGE could not tell) and PENDING (still in progress) are not. Use it before you tell anyone the work is done. A check that finds something new is billed; asking again when nothing has changed is free.

Input parameters:

- `authorization` (string, required): The authorization id brydge_supervise returned for the action.

Output parameters:

- `agentAgreed` (boolean|null)
- `authorization` (string)
- `because` (string)
- `checkedAt` (string|null)
- `claimed` (string|null)
- `externalRef` (string|null)
- `reason` (string|null)
- `replayed` (boolean)
- `state` (string)

### `brydge_get_finding` (~72 tokens)

What BRYDGE has found so far

What BRYDGE has already found about an action, without reading the records again. Free. BRYDGE checks each action by itself once the destination's reporting window has passed; until then this says PENDING.

Input parameters:

- `authorization` (string, required): The authorization id brydge_supervise returned for the action.

Output parameters:

- `agentAgreed` (boolean|null)
- `authorization` (string)
- `because` (string)
- `checkedAt` (string|null)
- `claimed` (string|null)
- `externalRef` (string|null)
- `reason` (string|null)
- `replayed` (boolean)
- `state` (string)

### `brydge_get_headroom` (~80 tokens)

How much you may do without a person

How many actions of this kind you may take in any 24 hours before a person is asked, how many are left, and what raises or lowers that. Every report BRYDGE checks and finds true raises it.

Input parameters:

- `action` (string, required): The kind of work, as it is set up in BRYDGE, such as refund.

Output parameters:

- `action` (string)
- `actions` (number)
- `earned` (number)
- `lowers` (string)
- `raises` (string)
- `remaining` (number)
- `says` (string)
- `used` (number)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-brydge-ai-brydge/brydge-mcp#diagnostics

## Score history

- 2026-09-27: 71
- 2026-09-26: 60

## Common questions

### What is the BRYDGE MCP server?

BRYDGE is an MCP server listed in the public MCP registry as com.brydge-ai/brydge. Checks whether an agent's actions actually happened, against the destination's own records. This page covers its npm package (brydge-mcp).

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

BRYDGE scores 71 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 27 September 2026. It declares no install or post-install scripts. 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 BRYDGE MCP server expose?

BRYDGE exposes 5 tools: brydge_supervise, brydge_report_outcome, brydge_verify, brydge_get_finding, brydge_get_headroom. Their descriptions and schemas cost roughly 631 tokens of context every time the server is loaded.

### Is the BRYDGE MCP server still maintained?

BRYDGE 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.

### What licence is the BRYDGE MCP server under?

BRYDGE declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/brydge-mcp
- Socket report: https://socket.dev/npm/package/brydge-mcp
- Repository: https://github.com/contactkontey-dotcom/brydge-mcp
- Website: https://www.brydge-ai.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-brydge-ai-brydge/brydge-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-brydge-ai-brydge/brydge-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-brydge-ai-brydge/brydge-mcp