{"id":"slzcdhd-1mcp","name":"1mcp","homepage":null,"repo_url":"https://github.com/slzcdhd/1mcp","category":"infrastructure","subcategories":[],"tags":["mcp","proxy","aggregation","streamable-http","nodejs","typescript","tool-calling","stdio","sse","configuration-hot-reload"],"what_it_does":"1mcp is a central proxy/hub that aggregates multiple upstream MCP servers and exposes a unified streamable-http MCP interface to downstream clients. It discovers upstream tools/resources/prompts, prefixes capability names (e.g., serverName___toolName), routes downstream requests to the correct upstream server, and supports dynamic hot-reloading of the upstream server configuration with live capability updates.","use_cases":["Unifying multiple MCP servers behind a single HTTP endpoint for downstream MCP clients","Capability discovery/aggregation across heterogeneous upstream transports (stdio/SSE/streamable-http)","Dynamic operations where upstream servers can be added/removed/updated without restarting the hub","Simplifying tool calling by standardizing capability naming via prefixes"],"not_for":["Production deployments requiring strong, documented access control on the hub itself (auth is not clearly specified for /mcp)","Environments where you cannot run/allow upstream server processes (stdio via command)","Use as a general-purpose API gateway beyond MCP proxying/routing"],"best_when":"You want an MCP “hub” that consolidates tools from multiple upstream MCP servers and you’re comfortable managing upstream connections through a local configuration file.","avoid_when":"You need a hosted SaaS with SLAs, explicit rate limiting, and documented security guarantees for external clients hitting the hub.","alternatives":["Use a single upstream MCP server directly (no aggregation)","Build a lightweight custom MCP router using @modelcontextprotocol/sdk","Use other MCP proxy/hub implementations if they provide stronger auth/rate-limit guidance","Deploy upstream servers behind your own reverse proxy/load balancer (if you already have a single MCP endpoint)"],"af_score":49.5,"security_score":34.0,"reliability_score":28.8,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T21:23:33.857147+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":"POST /mcp (streamable-http) on the configured host/port","has_sdk":true,"sdk_languages":["TypeScript","JavaScript"],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["None documented for the hub itself","Upstream servers may require auth via their own transport headers (e.g., SSE/streamable-http examples)"],"oauth":false,"scopes":false,"notes":"Authentication/authorization for 1mcp’s downstream interface (/mcp) is not explicitly documented. The README only shows examples of upstream headers for SSE/streamable-http upstream connections, which does not guarantee the hub enforces auth for clients."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Self-hosted open-source package (MIT per README). No pricing model described."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":49.5,"security_score":34.0,"reliability_score":28.8,"mcp_server_quality":70.0,"documentation_accuracy":78.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":40.0,"rate_limit_clarity":5.0,"tls_enforcement":30.0,"auth_strength":30.0,"scope_granularity":20.0,"dependency_hygiene":50.0,"secret_handling":45.0,"security_notes":"Hub access control is not clearly documented; relying on network controls is likely. TLS enforcement is not specified in the README. Upstream connections may include Authorization/API-key headers, but there’s no guidance on secret storage/logging practices. Dependency list is small and includes core libraries (@modelcontextprotocol/sdk, express, eventsource), but no vulnerability/patching policy is stated.","uptime_documented":0.0,"version_stability":45.0,"breaking_changes_history":0.0,"error_recovery":70.0,"idempotency_support":"false","idempotency_notes":"No explicit idempotency guidance for MCP methods. Some methods (like tool calls) may not be idempotent depending on upstream tools.","pagination_style":"none","retry_guidance_documented":true,"known_agent_gotchas":["Capability names are prefixed with serverName___, so agents must use the prefixed name when calling through the hub.","Upstream reconnection and dynamic capability updates can change available capabilities during runtime.","Session management is described as having a 30-minute timeout/inactivity cleanup in places, but the README also contains an apparent inconsistency saying sessions persist indefinitely; agents should be prepared for session expiration/cleanup.","Dynamic config hot-reload may briefly invalidate/refresh capability mappings during changes.","Upstream servers that are unreachable will prevent certain capabilities from being routed successfully; agents should handle tool-not-found/connection errors."]}}