{"id":"rvoh-emccaleb-portkey-mcp-server","name":"portkey-mcp-server","homepage":null,"repo_url":"https://github.com/rvoh-emccaleb/portkey-mcp-server","category":"ai-ml","subcategories":[],"tags":["mcp","model-context-protocol","portkey","prompts","go","stdio","sse","jsonrpc","tool-calling"],"what_it_does":"Provides an MCP (Model Context Protocol) server that bridges AI tool/service integrations to Portkey, exposing MCP tools for creating prompts, rendering prompts, and listing prompts via Portkey APIs. Supports both stdio and SSE (HTTP) transports.","use_cases":["Integrate Portkey prompt management/rendering into MCP-compatible AI clients (e.g., Cursor, Claude Desktop via stdio)","Render and manage Portkey prompts programmatically through an MCP tool interface","Local/dev bridging for agents/tools that speak MCP but need to use Portkey prompt endpoints"],"not_for":["Production use where transport security, rate limiting, and error semantics must be tightly guaranteed without reviewing server code/config"],"best_when":"You can run the MCP server locally (stdio or SSE) and you have a Portkey API key configured via environment variables.","avoid_when":"You require a managed SaaS with published uptime/SLA, fine-grained scopes, or turnkey auth/rate-limit guarantees without inspecting the Go server implementation.","alternatives":["Use Portkey APIs directly instead of MCP (admin/control-plane + inference endpoints)","Use an MCP-to-HTTP proxy/gateway you control (with OpenAPI-defined contracts)","Implement a small MCP server wrapper around the Portkey REST APIs"],"af_score":60.5,"security_score":47.5,"reliability_score":26.2,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T19:52:13.941955+00:00","interface":{"has_rest_api":true,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":"http://localhost:8080/sse (in SSE mode)","has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["Environment variable PORTKEY_API_KEY (in Docker/binary usage)"],"oauth":false,"scopes":false,"notes":"Authentication is via a Portkey API key provided as an environment variable. The README does not describe scope granularity or token scopes for the MCP server itself."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Pricing for the Portkey backend is not described in this repository README."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":60.5,"security_score":47.5,"reliability_score":26.2,"mcp_server_quality":78.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":90.0,"rate_limit_clarity":10.0,"tls_enforcement":45.0,"auth_strength":60.0,"scope_granularity":20.0,"dependency_hygiene":50.0,"secret_handling":60.0,"security_notes":"Uses HTTPS/TLS behavior is not documented; SSE example uses http://localhost. Auth appears to rely on a single PORTKEY_API_KEY environment variable with no documented scopes or rotation guidance. No information provided on dependency vulnerabilities, secret logging redaction, or transport hardening—would require code/config review.","uptime_documented":0.0,"version_stability":45.0,"breaking_changes_history":30.0,"error_recovery":30.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["SSE transport requires keeping the initial SSE connection open for the duration of the MCP session","README provides manual SSE call sequence but does not document server-side timeouts, reconnection behavior, or retry/idempotency characteristics for tool calls"]}}