ThinMCP
Provides a gateway to interact with upstream Cloudflare MCP servers, allowing for operations such as listing DNS zones and managing cloud resources through compressed search and execution tools.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ThinMCPsearch for Cloudflare tools and list my active zones"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ThinMCP
ThinMCP is an MCP gateway that exposes many upstream MCP servers through a stable two-tool interface:
search()execute()
Instead of loading every upstream tool definition into model context, ThinMCP keeps a local catalog, lets the model discover tools on demand, and forwards only the calls it needs to make.
Why ThinMCP
Connecting multiple MCP servers directly to a model increases context size as tool count grows. ThinMCP keeps the model-facing surface area fixed while still allowing access to a large tool ecosystem.
The result is a simpler integration point for clients and a more predictable runtime shape for production deployments.
Related MCP server: MCP Gateway
Architecture
flowchart LR
A["LLM or MCP Client"] --> B["ThinMCP Gateway"]
B --> C["Local Catalog"]
B --> D["Execution Layer"]
D --> E["Schema Validation"]
E --> F["Upstream MCP Servers"]
G["Sync Process"] --> F
G --> C
G --> H["Snapshots"]Key Capabilities
Fixed two-tool interface for the model
Support for HTTP and stdio upstream servers
Local SQLite-backed catalog for discovery
Input validation before upstream execution
Sandboxed execution for gateway tool calls
HTTP transport with health and metrics endpoints
Periodic sync of upstream tool metadata
Quick Start
npm install
npm run build
cp config/mcp-sources.example.yaml config/mcp-sources.yamlEdit config/mcp-sources.yaml, then sync and start:
npm run sync
npm startHTTP mode:
npm start -- --transport http --port 8787Validate the setup:
npm run doctorConfiguration
ThinMCP reads config/mcp-sources.yaml. Each upstream server can use either http or stdio transport.
Minimal example:
servers:
- id: exa
name: Exa MCP
transport: http
url: https://mcp.exa.ai/mcp
auth:
type: bearer_env
env: EXA_API_KEY
allowTools: ["*"]
- id: local-fs
name: Local Filesystem MCP
transport: stdio
command: npx
args:
- -y
- "@modelcontextprotocol/server-filesystem"
- /tmp
cwd: .
allowTools:
- "filesystem.*"
sync:
intervalSeconds: 300
onStart: true
runtime:
codeTimeoutMs: 15000
maxCodeLength: 20000
maxResultChars: 60000
catalog:
dbPath: ../data/thinmcp.db
snapshotDir: ../snapshotsUse allowTools to keep each upstream server scoped to the tools you actually want exposed through the gateway.
Running ThinMCP
Development:
npm run devProduction build:
npm run build
npm startHTTP mode:
npm start -- --transport http --host 127.0.0.1 --port 8787Available HTTP endpoints:
/mcp/healthz/metrics
Operations
Common commands:
npm run build
npm run sync
npm run doctor
npm test
THINMCP_RUN_E2E=1 npm run test:e2eOperational guidance:
Keep upstream credentials in environment variables
Restrict
allowToolsto the smallest useful surface areaEnable HTTP auth and rate limiting when exposing the gateway beyond local development
Run
npm run syncas part of deployment or startup validation if catalog freshness matters
Client Integration
Client examples are documented in docs/CLIENT_INTEGRATIONS.md.
License
ISC
This server cannot be deployed
Maintenance
Related MCP Connectors
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceA universal gateway that aggregates multiple MCP servers into a single interface while providing advanced token optimization, result filtering, and automated summarization. It enables efficient management of large tool catalogs and reduces context usage by up to 95% for major AI clients.13 npm15MIT
- AlicenseNot gradedqualityCmaintenanceAggregates multiple Model Context Protocol servers into a single gateway to provide unified search, description, and execution of tools. It reduces context limit issues by dynamically fetching specific tool schemas only when needed rather than loading all available tools at once.13 npm22MIT
- AlicenseNot gradedqualityBmaintenanceA single MCP endpoint for AI agents to browse, inspect, and call tools from multiple upstream MCP servers without loading all schemas upfront, reducing context overhead.11 npmISC
- AlicenseNot gradedqualityCmaintenanceA unified MCP gateway that reduces context token usage by exposing all services through just two tools (search and execute), supporting built-in services like Asana and Sentry as well as proxied external MCP servers.8 npm1MIT