{"id":"agency-ai-solutions-openai-codex-mcp","name":"openai-codex-mcp","homepage":null,"repo_url":"https://github.com/agency-ai-solutions/openai-codex-mcp","category":"devtools","subcategories":[],"tags":["mcp","json-rpc","code-generation","developer-tools","fastapi","uvicorn","cli-bridge"],"what_it_does":"Provides an MCP server (JSON-RPC over HTTP) that exposes methods (e.g., codex_completion, write_code, explain_code, debug_code) to route requests to the OpenAI Codex CLI for code generation, explanation, and debugging. Designed for use with tools like Claude Code.","use_cases":["Integrate an OpenAI Codex CLI workflow into an MCP-capable agent/tool for code generation","Request structured code outputs for a specified language via a dedicated MCP method","Ask for explanations of provided code via MCP","Debug/fix code given an issue description via MCP"],"not_for":["Production-grade deployments that require strong authentication/authorization controls at the MCP server boundary","Use cases needing stable OpenAPI/typed SDK contracts for programmatic integration beyond raw JSON-RPC","Environments where HTTP access to the server must be strictly controlled (since the README shows no MCP-side authentication)"],"best_when":"You want a lightweight local (localhost) bridge between an MCP-capable client and the @openai/codex CLI for developer-assistant coding tasks.","avoid_when":"You cannot restrict network access to the MCP server (e.g., leaving it exposed without authentication), or you need formal API contracts (OpenAPI) and explicit rate-limit/timeout/error semantics.","alternatives":["Use Claude Code tools without MCP and call Codex directly (or via a web API proxy you control)","Implement a small internal wrapper service around the Codex CLI with explicit auth, structured errors, and documented rate limits","Use an OpenAI-native API integration directly in the agent framework instead of going through the Codex CLI"],"af_score":39.8,"security_score":22.5,"reliability_score":25.0,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T15:22:16.104879+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":"http://localhost:8000/","has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["None (README instructs leaving Authentication blank for Claude Code tool registration)"],"oauth":false,"scopes":false,"notes":"Authentication is not described for the MCP server; the manual Claude Code setup instructs leaving authentication blank. Any real auth would need to be verified from the implementation, which is not included here."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information for the MCP server is provided. Costs would come from using the Codex CLI / underlying OpenAI usage."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":39.8,"security_score":22.5,"reliability_score":25.0,"mcp_server_quality":55.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":20.0,"rate_limit_clarity":5.0,"tls_enforcement":20.0,"auth_strength":20.0,"scope_granularity":0.0,"dependency_hygiene":50.0,"secret_handling":30.0,"security_notes":"The README shows the server registered with no authentication and uses http://localhost:8000/ in examples, suggesting minimal transport/security guidance. The server depends on running an external Codex CLI configured with an OpenAI API key; secure handling of that key is not described here. No information is provided about TLS enforcement, request logging redaction, CSRF protection, or rate limiting.","uptime_documented":0.0,"version_stability":35.0,"breaking_changes_history":40.0,"error_recovery":25.0,"idempotency_support":"false","idempotency_notes":"Not documented; operations likely trigger non-idempotent code generation via an external CLI/model call.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["The MCP server forwards to the Codex CLI; behavior/latency and error semantics may be inherited from the CLI invocation rather than clearly specified here.","Authentication is not described for the server; agents may assume the tool is safe to call only locally/within a trusted network.","Rate limits, timeouts, and structured error codes are not documented in the provided README; agent retry/backoff strategies may be guesswork."]}}