{"id":"robryanx-temporal-mcp-server","name":"temporal-mcp-server","homepage":null,"repo_url":"https://github.com/robryanx/temporal-mcp-server","category":"devtools","subcategories":[],"tags":["mcp","temporal","workflow-history","debugging","observability","go","api-integration"],"what_it_does":"Provides an MCP server that connects to a Temporal server to expose Temporal workflow history via an MCP tool (workflow_history) and a documentation-like MCP resource (test://resource).","use_cases":["Inspect and reason about Temporal workflow execution history from an AI agent","Debug workflow behavior by retrieving event history by workflow_id and run_id","Build agent-assisted observability/workflow forensics using MCP tool calls"],"not_for":["Triggering or mutating workflow state (based on available docs, it is read-only history exposure)","Production-grade secure multi-tenant deployment without additional auth/network controls","Use where workflow history must be constrained by fine-grained authorization"],"best_when":"You need an MCP-compatible way to fetch Temporal workflow history for debugging/analysis and you can control access to the MCP server and Temporal backend.","avoid_when":"You cannot restrict access to potentially sensitive workflow history data, or you require robust documented error semantics, rate limiting, and pagination behavior.","alternatives":["Temporal Web UI and CLI for workflow inspection","Custom MCP server exposing a vetted subset of Temporal APIs","Direct Temporal SDK/API calls from your application (bypassing MCP)"],"af_score":42.8,"security_score":36.2,"reliability_score":22.5,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T21:21:27.384426+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":["Go"],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":[],"oauth":false,"scopes":false,"notes":"No authentication/authorization mechanism is described in the provided README. Access control should be assumed to be handled outside the service (e.g., network restrictions) unless implemented in code not shown 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 provided."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":42.8,"security_score":36.2,"reliability_score":22.5,"mcp_server_quality":55.0,"documentation_accuracy":60.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":35.0,"rate_limit_clarity":10.0,"tls_enforcement":60.0,"auth_strength":20.0,"scope_granularity":20.0,"dependency_hygiene":35.0,"secret_handling":50.0,"security_notes":"README lists connection/env configuration but does not document TLS requirements, authentication, authorization scopes, or secret handling practices. Workflow history can contain sensitive data; ensure MCP endpoint is protected and that Temporal access is least-privilege. Scores reflect missing documented security controls in the provided materials.","uptime_documented":0.0,"version_stability":35.0,"breaking_changes_history":30.0,"error_recovery":25.0,"idempotency_support":"true","idempotency_notes":"The primary tool described is a history retrieval operation, which is inherently idempotent (read-only), assuming the implementation does not trigger side effects.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Tool interface is only lightly documented; argument validation, required fields beyond workflow_id/run_id, and response format are not specified in README.","No guidance on pagination/limits for large histories; agents may need to handle truncation or timeouts if the server returns limited history.","No documented retry/backoff behavior; agents should implement safe retries on transient failures only."]}}