| FMRS | 61 / 100 · C | 79 / 100 · B |
|---|
| Reliability | 10 / 20 | 12 / 20 |
|---|
| Security and permissions | 12 / 20 | 18 / 20 |
|---|
| Maintenance | 10 / 20 | 16 / 20 |
|---|
| Documentation | 16 / 20 | 18 / 20 |
|---|
| Setup experience | 13 / 20 | 15 / 20 |
|---|
| Best for | - Pi coding-agent users who want lower MCP context overhead
- Developers who need access to multiple MCP ecosystem services
- Users who want lazy connections, metadata caching, or optional direct tool registration
| - Engineering teams scaling AI coding agents while controlling spend
- Platform teams that need auditable, rollback-aware agent execution records
- Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
|
|---|
| Not for | - Users who do not use Pi
- Workflows requiring server-process sharing across Pi sessions
- MCP sampling workflows requiring context inclusion, tools, stop sequences, audio, or image content
| - Developers who just want a simple code-completion helper without run governance
- Teams unwilling to accept local JSONL run records with HMAC signing
- Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
|
|---|
| Required permissions | - Read and write Pi MCP configuration, tool metadata caches, and OAuth credential directories
- Start configured local MCP processes and access their working directories
- Access configured HTTP MCP endpoints, headers, environment variables, and OAuth credentials
- Depending on the configured MCP servers, access files, browsers, databases, APIs, or other external resources
| - Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
- Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
- Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
- Execution of user-configured verifier commands (e.g. npm test)
|
|---|
| Risks and side effects | - Configured MCP servers may receive the file, network, database, or API access required by their configuration and use
- OAuth authorization URLs, codes, and tokens are sensitive credentials
- Oversized text results may be written to the system temporary directory and are not cleaned up automatically
- Review imported host configurations and their permission scope before relying on them
| - Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
- Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
- Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
- Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
|
|---|
| Supported clients | Pi | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 1 | 0 |
|---|