CAPI is a lightweight API Gateway and load balancer that enables service discovery and proxying for REST APIs, WebSockets, and SSE, utilizing HashiCorp Consul for service registration and management.
From the registry: Apache Camel API Gateway with REST-to-MCP bridging for LLM agents.
Please install the `capi-core` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **HashiCorp Consul** — CAPI discovers services from HashiCorp Consul
- **Config file** — Provide a CAPI YAML config and set CAPI_CONFIG_FILE
- **Run CAPI Gateway** — Run via Docker, Helm, or Java JAR. Example: `docker run -p 8380:8380 -p 8381:8381 -v $(pwd)/config/config.yaml:/capi/config/config.yaml -e CAPI_CONFIG_FILE=/capi/config/config.yaml surisoft/capi-core`
Canonical MCP server config (HTTP transport):
- url: `http://<your-capi-host>:8380/mcp`
Note: CAPI is an API gateway whose experimental MCP Gateway bridges existing REST services (registered in Consul) and real MCP servers into a unified MCP endpoint (JSON-RPC 2.0 over Streamable HTTP). Not an installable MCP server itself — you run CAPI as an API gateway and it exposes /mcp.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CAPI_CONFIG_FILErequiredPoints to a valid configuration file.MCP server that exposes GraphQL operations as tools for AI models.