{"id":"agentrpc-agentrpc","name":"AgentRPC","homepage":null,"repo_url":"https://github.com/agentrpc/agentrpc","category":"devtools","subcategories":[],"tags":["rpc","agent-infrastructure","mcp","multi-language","private-network","observability"],"what_it_does":"AgentRPC is a universal RPC layer that allows AI agents to connect to functions deployed anywhere (private VPCs, Kubernetes, multi-cloud) across network boundaries and language barriers. It wraps functions in an RPC interface exposed via MCP and OpenAI-compatible tool definitions.","use_cases":["Connecting AI agents to private backend functions without exposing open ports","Calling functions across language boundaries (TypeScript, Go, Python, .NET)","Building observability and health tracking into agent-function interactions","Orchestrating long-running async functions that exceed HTTP timeout limits","Enabling Claude Desktop, Cursor, and other MCP-compatible agents to call registered tools"],"not_for":["Simple function calls that don't need multi-language support or private network access","Real-time latency-critical applications (introduces network hop through hosted platform)","Scenarios where exposing API keys to agents is a security concern","Applications that cannot depend on external hosted service (api.agentrpc.com)"],"best_when":"You have functions deployed in private networks and need agents to call them securely without exposing infrastructure, or when you need consistent function calling across multiple languages and frameworks integrated with MCP.","avoid_when":"You need sub-second latency, cannot trust external SaaS platforms, or are calling simple synchronous functions that don't require the abstraction layer.","alternatives":["Direct REST APIs with agent frameworks (OpenAI SDK, Anthropic SDK)","gRPC with custom agent adapters","AWS Lambda + API Gateway for cloud-native setups","Custom MCP server implementations without the hosted platform"],"af_score":56.8,"security_score":60.0,"reliability_score":40.0,"package_type":"mcp_server","discovery_source":["github_awesome"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T22:11:47.516010+00:00","interface":{"has_rest_api":true,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":true,"sdk_languages":["TypeScript","Go","Python"],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["API Key (AGENTRPC_API_SECRET)"],"oauth":false,"scopes":false,"notes":"Uses API secret for MCP server authentication; unclear if scoped permissions available or if key grants all access to all registered functions."},"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 in README or metadata; appears to be early-stage project with pricing model not yet public."},"requirements":{"requires_signup":true,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":56.8,"security_score":60.0,"reliability_score":40.0,"mcp_server_quality":70.0,"documentation_accuracy":65.0,"error_message_quality":0.0,"error_message_notes":"README mentions error handling as a feature but provides no examples or documentation of actual error responses; cannot assess error message quality from available information.","auth_complexity":85.0,"rate_limit_clarity":20.0,"tls_enforcement":85.0,"auth_strength":70.0,"scope_granularity":30.0,"dependency_hygiene":50.0,"secret_handling":60.0,"security_notes":"Relies on API secret as primary auth; no granular scopes documented. Environment variable-based secret passing is good practice, but examples show secrets in config files (claude_desktop_config.json) which could expose them. Hosted platform acts as trust boundary — all agent requests flow through api.agentrpc.com. Early-stage project (created March 2025, 129 stars) with limited security track record. No published security audit or disclosure policy visible.","uptime_documented":20.0,"version_stability":45.0,"breaking_changes_history":65.0,"error_recovery":30.0,"idempotency_support":"false","idempotency_notes":"No mention of idempotency guarantees in README or metadata; critical for agent use where retries are common.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["API secret must be passed via environment variables; if exposed in agent configs (e.g., claude_desktop_config.json), credentials are readable by code inspection","MCP server launched locally via 'npx agentrpc mcp' — requires agent runtime to execute this command; integration model unclear","No documented retry behavior or backoff strategy; agents will need their own retry logic","Rate limiting not documented; agents may hit limits without guidance","No idempotency guarantees documented; retried calls may have side effects"]}}