# FINOS MCP - AI Governance (community) (pypi · finos-mcp-aigf)

Read-only MCP for FINOS AI governance risks, controls and crosswalks. Independent project.

- Trust score: 82/100 (high trust)
- Change this week: +19
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- pypi · `finos-mcp-aigf`: 82/100 (this document), [markdown](https://verifymcp.io/servers/vardhjain-finos-mcp-aigf/finos-mcp-aigf.md), [page](https://verifymcp.io/servers/vardhjain-finos-mcp-aigf/finos-mcp-aigf)

## Channel facts

- Registry: `pypi`
- Package: `finos-mcp-aigf`
- Version: `0.3.2`
- 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 2026-11-04.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 35 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to vardhjain/finos-mcp).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 8 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 66/100
  - 67% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1057 tokens (~88/item across 12 items; 11 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% 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 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 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 FINOS MCP - AI Governance (community) server?

FINOS MCP - AI Governance (community) runs locally as a PyPI package, launched with uvx finos-mcp-aigf. 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 vardhjain-finos-mcp-aigf -- uvx finos-mcp-aigf
```

### Cursor

```json
{
  "mcpServers": {
    "vardhjain-finos-mcp-aigf": {
      "command": "uvx",
      "args": [
        "finos-mcp-aigf"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "vardhjain-finos-mcp-aigf": {
      "command": "uvx",
      "args": [
        "finos-mcp-aigf"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add vardhjain-finos-mcp-aigf -- uvx finos-mcp-aigf
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "vardhjain-finos-mcp-aigf": {
      "type": "local",
      "command": [
        "uvx",
        "finos-mcp-aigf"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add vardhjain-finos-mcp-aigf --command uvx --arg finos-mcp-aigf
```

### Hermes

```yaml
mcp_servers:
  vardhjain-finos-mcp-aigf:
    command: "uvx"
    args: ["finos-mcp-aigf"]
```

### Netclaw

```json
{
  "McpServers": {
    "vardhjain-finos-mcp-aigf": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "finos-mcp-aigf"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add vardhjain-finos-mcp-aigf -t stdio -c uvx -a finos-mcp-aigf
```

### Other

```json
{
  "mcpServers": {
    "vardhjain-finos-mcp-aigf": {
      "command": "uvx",
      "args": [
        "finos-mcp-aigf"
      ]
    }
  }
}
```

## 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.

### 2026-11-04 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 81, +3)

- [functional improvement] Stability: unverified → 0.23

### 2026-10-29 (score 78, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-26 (score 63)

First indexed and scored.

## MCP tools (11)

### `list_risks` (~73 tokens)

List AIGF risks. Filter by type (RC = regulatory and compliance, OP = operational,
SEC = security) or document status. Returns ids you can pass to get_risk.

Input parameters:

- `page` (integer)
- `page_size` (integer)
- `status`
- `type`

Output parameters:

- `items` (array)
- `page` (integer)
- `page_size` (integer)
- `total` (integer)

### `get_risk` (~80 tokens)

Get one AIGF risk by id (AIR-SEC-010, ri-10, 10, or its title), with the controls that
mitigate it, related risks, and external references. Set include_sections=false for a
compact record without the full text.

Input parameters:

- `id` (string, required)
- `include_sections` (boolean)

Output parameters:

- `citation_uri` (string)
- `id` (string)
- `mitigated_by` (array)
- `references` (array)
- `related_risks` (array)
- `sections` (array)
- `sequence` (integer)
- `short_id` (string)
- `source_path` (string)
- `status` (string)
- `summary` (string)
- `title` (string)
- `type` (string)
- `type_label` (string)

### `list_controls` (~68 tokens)

List AIGF controls (the framework calls them mitigations). Filter by type
(PREV = preventative, DET = detective) or status. Returns ids for get_control.

Input parameters:

- `page` (integer)
- `page_size` (integer)
- `status`
- `type`

Output parameters:

- `items` (array)
- `page` (integer)
- `page_size` (integer)
- `total` (integer)

### `get_control` (~90 tokens)

Get one AIGF control by id (AIR-PREV-020, mi-20, 20, or its title), with the risks it
mitigates, related controls, and crosswalk references (NIST SP 800-53, ISO 42001, ...).
Set include_sections=false for a compact record.

Input parameters:

- `id` (string, required)
- `include_sections` (boolean)

Output parameters:

- `citation_uri` (string)
- `id` (string)
- `mitigates` (array)
- `references` (array)
- `related_controls` (array)
- `sections` (array)
- `sequence` (integer)
- `short_id` (string)
- `source_path` (string)
- `status` (string)
- `summary` (string)
- `title` (string)
- `type` (string)
- `type_label` (string)

### `map_risks_to_controls` (~158 tokens)

Map risks to the controls that mitigate them. Pass explicit risk_ids (up to 25), a
free-text query (the top k matching risks are used), and/or up to 5 queries (each
contributing its own top k matches, unioned with everything else) -- useful for
"both X and Y" questions where a single query blurs together two distinct concepts.
Controls are ordered by how many of the given risks they cover; control_type (PREV or
DET) restricts the result. Reports uncovered risks and any inputs that did not resolve.

Input parameters:

- `control_type`
- `k` (integer)
- `queries`
- `query`
- `risk_ids`

Output parameters:

- `controls` (array)
- `edges` (array)
- `risks` (array)
- `uncovered_risks` (array): Risk ids with no mapped control.
- `unresolved` (array): Inputs that did not resolve to a risk.

### `map_control_to_external` (~95 tokens)

Crosswalk one control to external frameworks: NIST SP 800-53 r5, NIST AI 600-1,
ISO 42001, EU AI Act, OWASP LLM/ML/ASI, FFIEC, IOSCO, SR 11-7 and others. Optionally
restrict to the named frameworks (see list_reference_frameworks).

Input parameters:

- `frameworks`
- `id` (string, required)

Output parameters:

- `citation_uri` (string)
- `control_id` (string)
- `frameworks` (array)
- `refs` (array)
- `title` (string)

### `search_framework` (~105 tokens)

Search risks and controls with matching sections and citable source URIs.

For an unscoped question clearly asking for risks or for controls, rank those
record types first while retaining the other type as a fallback. This is a
stable partition of the original relevance-ranked results, not a new relevance
score. Questions asking for both kinds stay mixed; explicit scope always wins.

Input parameters:

- `k` (integer)
- `query` (string, required)
- `scope` (string)

Output parameters:

- `hits` (array)
- `query` (string)
- `scope` (string)

### `search_status` (~60 tokens)

Report search_framework's active retrieval mode: whether it is BM25-only
(lexical) or fused with dense semantic search (hybrid), and why -- e.g. the
\`semantic` extra is not installed, or a model failed to load.

Output parameters:

- `mode` (string)
- `model`
- `semantic_enabled` (boolean)
- `semantic_status` (string)

### `list_reference_frameworks` (~37 tokens)

List the external reference frameworks the AIGF crosswalks to, with entry counts and
how many risks and controls cite each.

Output parameters:

- `frameworks` (array)

### `find_by_external_reference` (~126 tokens)

Reverse crosswalk: find the AIGF risks and controls that cite an external reference,
e.g. key='sa-9' (NIST SP 800-53), 'llm01-2025' (OWASP LLM Top 10), 'c3-s2-a15' (EU AI
Act), 'A-6-2-6' (ISO 42001). Matching is case-insensitive and ignores punctuation;
optionally restrict to one framework name from list_reference_frameworks.

Input parameters:

- `framework`
- `key` (string, required)

Output parameters:

- `framework`
- `key` (string)
- `matches` (array)

### `server_info` (~25 tokens)

Describe this server: standard version, upstream provenance, exposed counts, latency, policy.

Output parameters:

- `counts` (object)
- `latency` (object)
- `name` (string)
- `policy` (object)
- `read_only` (boolean)
- `resources` (array)
- `standard` (string)
- `standard_version`
- `tools` (array)
- `upstream_commit`
- `upstream_ref`
- `upstream_repo`
- `version` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/vardhjain-finos-mcp-aigf/finos-mcp-aigf#diagnostics

## Score history

- 2026-11-04: 82
- 2026-11-03: 81
- 2026-11-02: 81
- 2026-11-01: 78
- 2026-10-31: 78
- 2026-10-30: 78
- 2026-10-29: 78
- 2026-10-28: 63
- 2026-10-27: 63
- 2026-10-26: 63

## Common questions

### What is the FINOS MCP - AI Governance (community) server?

FINOS MCP - AI Governance (community) is listed in the public MCP registry as io.github.vardhjain/finos-mcp-aigf. Read-only MCP for FINOS AI governance risks, controls and crosswalks. Independent project. This page covers its PyPI package (finos-mcp-aigf).

### Is the FINOS MCP - AI Governance (community) server safe to use?

FINOS MCP - AI Governance (community) scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. Its build provenance is signed and verified. 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 FINOS MCP - AI Governance (community) server expose?

FINOS MCP - AI Governance (community) exposes 11 tools: list_risks, get_risk, list_controls, get_control, map_risks_to_controls, and 6 more. Their descriptions and schemas cost roughly 917 tokens of context every time the server is loaded.

### Is the FINOS MCP - AI Governance (community) server still maintained?

FINOS MCP - AI Governance (community) is still listed as active in the MCP registry. We last reached this channel on 4 November 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 FINOS MCP - AI Governance (community) server under?

FINOS MCP - AI Governance (community) declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/finos-mcp-aigf/
- Socket report: https://socket.dev/pypi/package/finos-mcp-aigf
- Repository: https://github.com/vardhjain/finos-mcp
- Website: https://vardhjain.github.io/finos-mcp/
- Changelog RSS feed: https://verifymcp.io/servers/vardhjain-finos-mcp-aigf/finos-mcp-aigf.xml
- Changelog JSON feed: https://verifymcp.io/servers/vardhjain-finos-mcp-aigf/finos-mcp-aigf.json
- HTML version of this page: https://verifymcp.io/servers/vardhjain-finos-mcp-aigf/finos-mcp-aigf