Watchlist tracking
Reviewed for relevance and future tracking value.
MCP100 Assessment
Watchlist / Tracking
Why we’re tracking it
Follow-up value is specific to Deterministic codebase graph analysis exposed through fallow-mcp: Do graph-backed explanations retain traceable evidence as framework detection and exit contracts evolve?
Reviewed · Documentation review; complete setup workflow not independently tested
Best fit
Teams and agents auditing JavaScript/TypeScript code quality and architecture.
What we know
A Rust-native static-analysis and codebase-intelligence tool with CLI, LSP and MCP launcher.
Maintenance / activity evidence
- fallow 3.31.0 published 2026-09-30T17:09:16.979Z
Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.
Verification gaps / watch-outs
- Installation and comprehensive security have not been independently audited.
- Reads project source/config. Writes: fallow fix can modify code.
- Authentication not yet verified.
- Sensitive access: Source code
- Local analysis is bounded, but fix actions modify source and optional cloud features add external data flow.
Full authority, access and evidence limits are available in Review context and Access & risk.
Popularity
5,010 repository stars · 5.2M package downloads / 30 days
Stars observed Oct 6, 2026. Downloads observed Oct 6, 2026.
All limitations / Review context
Do graph-backed explanations retain traceable evidence as framework detection and exit contracts evolve?
The bounded review of the publisher's documented Deterministic codebase graph analysis exposed through fallow-mcp and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.
- Local analysis is bounded, but fix actions modify source and optional cloud features add external data flow.
- Reads project source/config.
- Analysis is local unless optional cloud features are used.
- Reviewed write actions: fallow fix can modify code
- Sensitive access: Source code
- Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
- Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
- Documented tool authority and any remote data handling must be checked before installation or use.
- Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
- Static analysis is not runtime coverage.
- Auto-fix can modify code; preview changes first.
Original activity observations
- fallow 3.31.0 published 2026-09-30T17:09:16.979Z
Technical identity
npm/fallow- Exact implementation source
- https://www.npmjs.com/package/fallow ↗
- Reviewed resource type
- Testing / Debugging
- Repository identity
- fallow-rs/fallow
- Package identity
- npm:fallow
Evidence & Sources
- Evidence basis
- Recorded source evidence
- Setup runtime verification
- Not independently runtime-tested by MCP100 for this setup workflow.
Reviewed · Latest source observation
- Package registry ↗
fallow
Recorded package identity, distribution or download evidence.
Includes references whose attribution is not established.
- GitHub repository ↗
fallow-rs/fallow
Repository reference; implementation attribution is not established for every document.
Includes references whose attribution is not established.
- Evidence source ↗
docs.fallow.tools/
Source material retained for this review.
Includes references whose attribution is not established.
Setup · Watchlist
Testing / Debugging setup
Publisher instructions.
Source evidence observed .
Additional setup details required — see the specific gaps below.
Set up testing / debugging integration
Publisher instructionsPublisher agent install modifies client configs/AGENTS.md and commit/push gates; preview dry-run first; do not run install in research | Publisher npm README revisited on 2026-10-14; exact identity retained.
Reviewed setup example · Publisher instructions
npm install --save-dev fallowReviewed setup example · Publisher instructions
npx fallow agent install --dry-runReviewed setup example · Publisher instructions
npx fallow agent installConfigure / authenticate
MCP100 setup guideProvides `fallow-mcp` launcher after installation. Use `npx fallow agent install --dry-run` then explicit install if approved; avoid installing hooks silently.
Previously reviewed configuration / prerequisites: MCP launcher is fallow-mcp, not fallow: add mcpServers command npx, args ["--yes","--package","fallow","fallow-mcp"], or project local pnpm exec fallow-mcp.
Check connection
Suggested check`npx fallow health --score` checks project CLI, inspect MCP tools separately.
Remove / uninstall / revoke
MCP100 setup guideIf your Claude Code MCP registration is named `fallow`, run the client removal command. For Claude Desktop/Cursor/Codex or another registered name, remove the matching entry in that host’s MCP settings. Hosted OAuth disconnect and stopping a self-hosted process are separate; npx has no permanent global package install.
Remove named client registration · Claude Code only · MCP100 composed guide
claude mcp remove fallow
Official Documentation & Sources
What it does
A Rust-native static-analysis and codebase-intelligence tool with CLI, LSP and MCP launcher.
- Capability
- Developer Tools
- Resource type
- Testing / Debugging
- Industry
- Software & Technology
- Best fit
- Teams and agents auditing JavaScript/TypeScript code quality and architecture.
Representative uses
- Find unused code and cycles
- Detect duplication and complexity
- Run changed-file audits
- Expose findings and fixes to agents
Limitations
- Static analysis is not runtime coverage.
- Auto-fix can modify code; preview changes first.
Reviewed access
Access & risk
Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.
- Authentication
- Not documented in the reviewed sources
- Permissions
- Reads project source/config.
- Data handling
- Analysis is local unless optional cloud features are used.
- Cost
- freemium
- Risk and cautions
- Local analysis is bounded, but fix actions modify source and optional cloud features add external data flow.
Access scope and cautions
- Write actions
- fallow fix can modify code
- Sensitive access
- Source code
- Risk level
- moderate
FAQ
Based on reviewed evidence as of 2026-10-06. Watchlist tracking is not a recommendation or a security certification.
Which implementation does this page cover?
Can it modify data or perform write operations?
What data-handling boundary should I consider?
What limitations and risks should I check before use?
Is this an official MCP?
fallow-rs is listed as First-party MCP in MCP100’s current evidence.