Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Gemini FAF

PYPI · GEMINI-FAF-MCP · SCANNED SEP 20

Persistent project context for Google Gemini. Python/FastMCP. IANA-registered .faf format.

Available components

pypi · gemini-faf-mcp 76
−1 this week 76 Trust /100
Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security91
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects starlette 0.52.1, reached via functions-framework > starlette. A fixed version is available. View diagnostics → Fail
  • Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 4 of 67 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 8 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability67
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1095 tokens (~84/item across 13 items; 13 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management80
  • Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the Gemini FAF MCP server?

Gemini FAF runs locally as a PyPI package, launched with uvx gemini-faf-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · gemini-faf-mcp

# add to Claude Code
claude mcp add one-faf-gemini-faf-mcp -- uvx gemini-faf-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "one-faf-gemini-faf-mcp": {
      "command": "uvx",
      "args": [
        "gemini-faf-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "one-faf-gemini-faf-mcp": {
      "command": "uvx",
      "args": [
        "gemini-faf-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add one-faf-gemini-faf-mcp -- uvx gemini-faf-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "one-faf-gemini-faf-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "gemini-faf-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add one-faf-gemini-faf-mcp --command uvx --arg gemini-faf-mcp
# ~/.hermes/config.yaml
mcp_servers:
  one-faf-gemini-faf-mcp:
    command: "uvx"
    args: ["gemini-faf-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "one-faf-gemini-faf-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "gemini-faf-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add one-faf-gemini-faf-mcp -t stdio -c uvx -a gemini-faf-mcp
// mcp.json
{
  "mcpServers": {
    "one-faf-gemini-faf-mcp": {
      "command": "uvx",
      "args": [
        "gemini-faf-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 19 Sept 26 +1
    • Stability: 0.97 → pass security
  • 18 Sept 26 −1
    • Stability: pass → 0.97 functional
  • 17 Sept 26 +1
    • Stability: 0.97 → pass security
  • 16 Sept 26 0
    • Package version: 2.5.1 → 2.8.2 functional
  • 15 Sept 26 +16
    • Malware scan: unverified → pass ▲ security
  • 14 Sept 26 −15
    • Malware scan: pass → unverified ▼ security
    • Package version: 2.5.1 → 2.8.2 functional
  • 13 Sept 26 +16
    • Malware scan: unverified → pass ▲ security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/gemini-faf-mcp@2.8.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Vulnerabilities 10 findings
ID CVE Severity Vector Fix available
GHSA-82w8-qh3p-5jfq CVE-2026-54283 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-86qp-5c8j-p5mr CVE-2026-48710 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N yes
GHSA-jp82-jpqv-5vv3 CVE-2026-54282 low CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N yes
GHSA-wqp7-x3pw-xc5r CVE-2026-48818 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N yes
GHSA-x746-7m8f-x49c CVE-2026-48817 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N yes
PYSEC-2026-161 CVE-2026-48710 none yes
PYSEC-2026-2280 CVE-2026-48817 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N yes
PYSEC-2026-2281 CVE-2026-48818 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N yes
PYSEC-2026-248 CVE-2026-54282 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N yes
PYSEC-2026-249 CVE-2026-54283 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 67 packages
Packages resolved 67
Stale 4
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 13 exposed · ~1,078 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
faf_about ~52

FAF format info — IANA registration, version, ecosystem. Returns metadata about the FAF format, server version, and available MCP bridges. Use this when users ask what FAF is or how it connects to other AI platforms.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

faf_agents ~118

Export and write AGENTS.md from a .faf file (non-destructive). Authors a BETTER-shaped AGENTS.md (setup · tests · layout · conventions · three-tier guardrails · definition of done · security · commit) via faf-python-sdk's authoring tool — in parity with faf-cli's `faf export --agents`. Injects it into AGENTS.md as a faf-managed block, preserving any hand content. Re-running updates the block in place — it never overwrites your file.

NameTypeReqDescription
pathstring––

Structured output declared, but exposes no named fields.

No examples provided.

faf_auto ~144

Auto-detect project stack and author/update a .faf file. Scans package.json, pyproject.toml, Cargo.toml, go.mod, and other manifest files for language, framework, database, API type, and build tools — then grounds the result in the repo's own files: docker-compose service images (Postgres, Redis, Elasticsearch...) map onto stack slots, and Makefile / justfile targets map onto test / build / lint commands. Facts from files, no hardcoded defaults. Creates a new .faf if none exists, or fills empty slots in an existing one.

NameTypeReqDescription
directorystring––
pathstring––

Structured output declared, but exposes no named fields.

No examples provided.

faf_context ~59

Get Gemini-optimized context from a .faf file. Returns the key sections an AI needs: project info, stack, instructions, and score. Use this to quickly understand a project without reading the full .faf structure.

NameTypeReqDescription
pathstring––

Structured output declared, but exposes no named fields.

No examples provided.

faf_discover ~56

Find .faf files in the project tree by walking up from start_dir. Searches the current directory and parent directories for project.faf. Use this before faf_read to locate the file automatically.

NameTypeReqDescription
start_dirstring––

Structured output declared, but exposes no named fields.

No examples provided.

faf_gemini ~112

Export and write GEMINI.md from a .faf file (non-destructive). Authors GEMINI.md in Gemini CLI's own convention (hierarchical, @file-importable — setup · verify · key files · stack · confirm-first actions) via faf-python-sdk's authoring tool, in parity with faf-cli's `faf export --gemini`. Injects it as a faf-managed block, preserving any hand content. Re-running updates the block in place.

NameTypeReqDescription
pathstring––

Structured output declared, but exposes no named fields.

No examples provided.

faf_init ~93

Create a starter .faf file with project name, goal, and language. Writes a valid FAF YAML file with all required sections. Will not overwrite an existing file — use faf_discover first to check. The path is confined to the project root (cwd / FAF_ALLOWED_ROOTS).

NameTypeReqDescription
goalstring––
languagestring––
namestring––
pathstring––

Structured output declared, but exposes no named fields.

No examples provided.

faf_migrate ~125

Migrate a .faf file to the current format version (3.0). Bumps `faf_version`, ensures the section roots exist (`project`, `stack`, `human_context`, `monorepo`), and re-serializes. Legacy slot names (`frontend`/`database`/…) still score via the registry's aliases — this only touches the version and structure, never your values. Parity with faf-cli's `faf migrate`. Pass dry_run=true to preview.

NameTypeReqDescription
dry_runboolean––
pathstring––

Structured output declared, but exposes no named fields.

No examples provided.

faf_model ~85

Get a 100% Trophy-scored example .faf file for a specific project type. Returns a complete, realistic project.faf that fills all 21 scored slots. Use this as a reference when building or improving a .faf file — shows exactly what 100% looks like. Call without arguments to list all 15 available project types.

NameTypeReqDescription
project_typestring––

Structured output declared, but exposes no named fields.

No examples provided.

faf_read ~55

Read project DNA from a .faf file. Returns the full parsed structure including project info, stack, preferences, and scoring data. Use this as the first step to understand any FAF-enabled project.

NameTypeReqDescription
pathstring––

Structured output declared, but exposes no named fields.

No examples provided.

faf_score ~63

Quick Mk4 score check — returns score (0-100%), tier, and slot counts. Uses the Mk4 Championship 21-slot scoring engine for universal parity. Use this for status checks; use faf_validate when you need error details.

NameTypeReqDescription
pathstring––

Structured output declared, but exposes no named fields.

No examples provided.

faf_stringify ~55

Convert parsed FAF data back to YAML string. Useful for displaying the raw .faf content or preparing it for editing. Reads the file, parses it, then re-serializes to clean YAML.

NameTypeReqDescription
pathstring––

Structured output declared, but exposes no named fields.

No examples provided.

faf_validate ~61

Validate a .faf file and return score, tier, and issues. Returns errors (must fix) and warnings (should fix) with specific messages. Use after faf_init or when checking if a .faf file meets quality standards.

NameTypeReqDescription
pathstring––

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the Gemini FAF MCP server?

Gemini FAF is an MCP server listed in the public MCP registry as one.faf/gemini-faf-mcp. Persistent project context for Google Gemini. Python/FastMCP. IANA-registered .faf format. This page covers its PyPI package (gemini-faf-mcp).

Is the Gemini FAF MCP server safe to use?

Gemini FAF scores 76 out of 100 on VerifyMCP. We recorded 10 known advisories against it as of 20 September 2026. 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 Gemini FAF MCP server expose?

Gemini FAF exposes 13 tools: faf_read, faf_validate, faf_score, faf_discover, faf_init, and 8 more. Their descriptions and schemas cost roughly 1,078 tokens of context every time the server is loaded.

Is the Gemini FAF MCP server still maintained?

Gemini FAF is still listed as active in the MCP registry. We last reached this channel on 20 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 Gemini FAF MCP server under?

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