faf-cliSAFE
The context every AI coding agent reads — authors AGENTS.md, CLAUDE.md, GEMINI.md & .cursorrules from your repo's real stack. IANA-registered .faf format.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
faf-cli CONTEXT, versioned.
The context every AI coding agent reads — authored from your repo, never guessed.
One `.faf` file → `AGENTS.md` · `CLAUDE.md` · `GEMINI.md` · `.cursorrules`, detected from your real stack, scored, and versioned with your code. No drift. No re-explaining.
[](https://github.com/modelcontextprotocol/servers/pull/2759) [](https://www.iana.org/assignments/media-types/application/vnd.faf+yaml) [](https://www.iana.org/assignments/media-types/application/vnd.fafm+yaml) [](https://www.iana.org/assignments/media-types/application/vnd.fafa+yaml) [](https://github.com/hesreallyhim/awesome-claude-code) [](https://www.npmjs.com/package/faf-cli) [](https://www.npmjs.com/package/faf-cli)
[](https://faf.one/downloads) · across npm, PyPI and crates.io · IANA-registered · Anthropic-merged (#2759)
⭐ Bookmarks it for you, helps other devs find it too.
[
17 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
HAND-TOOL | read | added by hand |
acme-web | read | The Acme storefront |
analytics_summary | read | faf analytics --summary - Performance metrics |
ask | read | Answer a FAF question. |
canary-7f3a-pkg | read | CANARY-7F3A description of a package.json kept outside the project |
chat | read | Talk |
cite | read | Return a citation. |
conductor-app | read | My conductor project |
conductor-e2e | read | E2E test |
demo | read | A demo service |
help_command | read | faf --help - Instant help display |
index_command | read | faf index - Universal A-Z reference |
repo-name | read | Repo description from package.json |
score_basic | read | faf score - Quick score check |
status_command | read | faf status - Git status equivalent speed |
t | read | A tool that does a useful thing for many developers. |
trust_dashboard | read | faf trust - Real-time trust calculation |
web | write | A deploy dashboard |
Trust audit
SAFEgrade B · trust 88/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (7 observation(s))
- Network
- declared (2 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (18)
.gemini/project.faf
parity-expected.fafb
.faf-dna
.fafignore
.taf
test.skipIf(!posix)('readFaf / readFafRaw / findFafFile: project.faf → ~/.aws/credentials', () => {sed -i '' "s|import \* as YAML from ['\"]yaml['\"]|import { parse as parseYAML, stringify as stringifyYAML } from '../../fix-once/yaml'|g" "$file"sed -i '' "s|import \* as YAML from ['\"]yaml['\"]|import { parse as parseYAML, stringify as stringifyYAML } from '../../../fix-once/yaml'|g" "$file"sed -i '' "s|import \* as yaml from ['\"]yaml['\"]|import { parse as parseYAML, stringify as stringifyYAML } from '../../fix-once/yaml'|g" "$file"sed -i '' "s|import \* as yaml from ['\"]yaml['\"]|import { parse as parseYAML, stringify as stringifyYAML } from '../../../fix-once/yaml'|g" "$file"sed -i '' "s|import yaml from ['\"]yaml['\"]|import { parse as parseYAML, stringify as stringifyYAML } from '../../fix-once/yaml'|g" "$file"expect(legacyStampNote('CLAUDE.md', `${OLD}`)).toBe(note('CLAUDE.md'));writeFileSync(f, `${'project:\n name: demo\n goal: A demo tool\n main_language: Go\n type: cli\nstack:\n database: None # HAND-CRLFBOM\n build: make # HAND-B\n'.replace(/\n/g, '\r\n')}`);expect(after.startsWith('project:\r\n')).toBe(true);writeFileSync(file, `${FAF_START}\nold body\n${FAF_END}\n\nuser-below-sentinel\n`);const yamlWithBom = '' + MINIMAL_FAF;
commander, faf-scoring-kernel, open, yaml, @faf/specification, @types/bun, @types/node, @typescript-eslint/eslint-plugin
faf-cli
Gates applied: no_behavioural_pass.
efa5d1f69643full audit observations/trust-audit/mcp-server/wolfe-jam__faf-cli.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | efa5d1f69643 | SAFE | B | 88 | first audit |
Questions
What is the faf-cli MCP server?
The context every AI coding agent reads — authors AGENTS.md, CLAUDE.md, GEMINI.md & .cursorrules from your repo's real stack. IANA-registered .faf format.
What tools does faf-cli expose?
18 in total: 17 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is faf-cli safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (88/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does faf-cli need?
It reads ANTHROPIC_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does faf-cli run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as faf at 6.5.1.
How current is this page?
The grade is for one exact copy of the source (efa5d1f69643), read on 2026-10-11. The repository is watched and re-audited when it changes.