M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionAnsible Automation Platform MCP ServerAn MCP service exposing Ansible Automation Platform APIs through OpenAPI specificationsMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS52 / 100 · D79 / 100 · B
Reliability9 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance10 / 2016 / 20
Documentation13 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Teams that already run Ansible Automation Platform and hold a valid AAP authentication token
  • Ops and automation engineers who want MCP clients to call AAP APIs with role- and permission-limited tool access
  • Offline or customized environments that need OpenAPI specs loaded from local files or custom URLs
  • 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 without an AAP instance or a valid token
  • Clients that require stdio local-process transport (this service is an HTTP endpoint)
  • Users expecting write operations to be enabled by default (writes require ALLOW_WRITE_OPERATIONS=true)
  • 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
  • A valid AAP authentication token (Authorization: Bearer or BEARER_TOKEN_OAUTH2_AUTHENTICATION)
  • A token with permission to access the AAP services in use
  • Write operations are disabled by default and require ALLOW_WRITE_OPERATIONS=true
  • Network access to the AAP base URL, or read access to configured local OpenAPI files
  • 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
  • Setting ignore-certificate-errors: true for development disables HTTPS certificate validation, enabling man-in-the-middle risk
  • With ALLOW_WRITE_OPERATIONS enabled, write operations allowed by the token can be performed and may modify or delete AAP resources unintentionally
  • The token appears in plain text on the command line, in environment variables, or in client configuration and may leak
  • Available tools and permissions depend on token permissions and toolset configuration; misconfiguration can expose more operations than intended
  • 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 clientsClaudeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00