| FMRS | 51 / 100 · D | 79 / 100 · B |
|---|
| Reliability | 4 / 20 | 12 / 20 |
|---|
| Security and permissions | 8 / 20 | 18 / 20 |
|---|
| Maintenance | 11 / 20 | 16 / 20 |
|---|
| Documentation | 15 / 20 | 18 / 20 |
|---|
| Setup experience | 13 / 20 | 15 / 20 |
|---|
| Best for | - Developers needing access to X data without a Twitter developer account.
- Building social listening, market research, CRM, or monitoring tools.
- Those needing multiple integration paths: REST, MCP, SDKs, webhooks.
- Teams wanting confirmation-gated publishing to ensure safety.
| - 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 | - Scenarios requiring full compliance with official Twitter API.
- Scenarios requiring real-time streaming (Streaming API).
- Accessing data or operations not supported by X Corp.
- Organizations with strict security requirements for non-official services.
| - 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 public X data (tweets, users, followers, etc.).
- Perform write operations like posting, replying, liking, following, after user confirmation.
- Create monitors, webhooks, export jobs, etc.
- Requires Xquik API key or OAuth 2.1 authorization.
- Certain operations require connected X account and explicit approval.
| - 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 | - Non-official service may violate X's terms of service.
- Third-party service may store or process data, consider privacy.
- Write operations require caution and may affect your account.
- Dependency on third-party service stability; may experience downtime.
| - 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 | Claude Desktop, Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Continue, OpenHands, Roo Code | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 2 | 0 |
|---|