에이전트 강화
게시자의 자체 명령입니다. PlugMCP 엔드포인트가 아닙니다.
Host a copy with our keys and logs.
uvx universal-connector-mcp==0.2.0Claude Code에는 로컬 명령용 설치 링크가 없습니다. 아래 명령을 복사해 터미널에서 실행합니다.
UCMCP_ALLOWED_HOSTS=<value> UCMCP_APIS_CONFIG=<value> UCMCP_CACHE_TTL=<value> UCMCP_BLOCK_PRIVATE_IPS=<value> GITHUB_TOKEN=<secret> claude mcp add io.github.teodormcp-universal-connector-mcp -- uvx universal-connector-mcp==0.2.0터미널에서 실행합니다.
{ "mcpServers": { "io.github.teodormcp-universal-connector-mcp": { "command": "uvx", "args": [ "universal-connector-mcp==0.2.0" ], "env": { "UCMCP_ALLOWED_HOSTS": "<value>", "UCMCP_APIS_CONFIG": "<value>", "UCMCP_CACHE_TTL": "<value>", "UCMCP_BLOCK_PRIVATE_IPS": "<value>", "GITHUB_TOKEN": "<secret>" } } }}claude_desktop_config.json
원격 URL인가요, 내 컴퓨터에서 실행하는 명령인가요? 두 설치 방식의 차이
PlugMCP에서 실행
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
실행게시자 제공
Stop installing a new MCP server for every service: point this one at any OpenAPI/Swagger, GraphQL, gRPC or SOAP spec - or pick one from the built-in catalog of - and your AI agent can call it. Securely, in fewer steps, with fewer tokens.
Security-first MCP server that connects any OpenAPI, GraphQL, gRPC or SOAP API to AI agents.
Most "universal API" MCP servers only speak REST/OpenAPI. This project is built around three differentiators:
Operation model with pluggable spec adapters (OpenAPI, GraphQL, gRPC, SOAP). Tools and executors never care which protocol produced an operation.
The agent explores APIs like a filesystem instead of loading hundreds of tools at once (which would blow up the context window on large APIs like Stripe). It searches for operations, inspects the ones it needs, then executes them.
flowchart TD
Agent["AI Agent"] -->|"MCP stdio"| Server["FastMCP Server"]
Server --> Tools["Meta-tools"]
Tools --> Registry["Operation Registry (normalized)"]
Adapters["Spec Adapters"] --> Registry
Tools --> Guard["Security Guard"]
Guard --> Executor["Protocol Executors"]
Executor --> Auth["Auth Manager"]
Executor --> UpstreamAPI["Upstream API"]
Where a per-API MCP server needs one tool round-trip per call - each returning a full JSON payload into the agent's context - this server collapses whole workflows:
extract - execute(..., extract=["items.*.name", "total_count"]) returns just those fields instead of a multi-kilobyte response. * fans out over arrays.execute_chained pipes step results into later params via ${save_as.path} references: one tool call instead of N.execute_chained(steps=[
[
{"operation_id": "github.repos_get", "params": {"owner": "o", "repo": "r"},
"save_as": "gh", "extract": ["stargazers_count"]},
{"operation_id": "open_meteo.get_v1_forecast", "params": {"latitude": 52.5, "longitude": 13.4},
"save_as": "weather", "extract": ["current_weather.temperature"]}
],
{"operation_id": "github.issues_list_for_repo",
"params": {"owner": "o", "repo": "r"}, "extract": ["*.title"]}
])
UCMCP_CACHE_TTL seconds (default 60), so repeated lookups are instant and free; pass fresh: true to bypass. Successful mutations invalidate that API's cached reads.You don't need to hunt for spec URLs. search_catalog searches two sources:
search_catalog(query="weather forecast")
-> [{"name": "open_meteo", "spec": "https://...forecast.yml", "base_url": "https://api.open-meteo.com", ...}]
load_api(spec="https://...forecast.yml", name="open_meteo", base_url="https://api.open-meteo.com")
execute(operation_id="open_meteo.get_v1_forecast", params={"latitude": 52.52, "longitude": 13.41, "hourly": "temperature_2m"})
The catalog is discovery-only: it returns spec URLs, never loads or executes anything itself, so the security guard still applies to everything you load from it.
The server runs in any MCP host via uvx - no manual install needed, the package is fetched from PyPI automatically (add [all] for GraphQL/gRPC/SOAP support):
{
"mcpServers": {
"universal-connector": {
"command": "uvx",
"args": ["universal-connector-mcp"],
"env": { "UCMCP_ALLOWED_HOSTS": "api.github.com" }
}
}
}
From source (development): pip install -e ".[all,dev]" and use "command": "universal-connector-mcp" instead. Extras: graphql, grpc, soap, keyring, all, dev; the core install supports OpenAPI/REST only.
One click via the badge above, or add the JSON block to .cursor/mcp.json in your project (shared with your team) or ~/.cursor/mcp.json (personal, all projects). See examples/mcp.json for a full config with credentials.
Add the same mcpServers block to claude_desktop_config.json (Settings > Developer > Edit Config).
claude mcp add universal-connector -- uvx universal-connector-mcp
Add the server under "servers" in .vscode/mcp.json:
{
"servers": {
"universal-connector": { "command": "uvx", "args": ["universal-connector-mcp"] }
}
}
All major MCP hosts accept the same mcpServers block shown above in their respective config files (~/.codeium/windsurf/mcp_config.json, Cline's MCP settings, etc.).
AI agents installing this server for a user: follow llms-install.md.
Point UCMCP_APIS_CONFIG at a YAML file to auto-load APIs at startup - see examples/apis.example.yaml.
You never edit config files to manage APIs - just tell your agent:
list_apis shows them.unload_api removes it (and from the remembered state).When an API needs credentials, load_api tells the agent exactly which environment variable to set (e.g. STRIPE_API_KEY), whether it is already configured, and the agent relays copy-pasteable instructions - you add the variable to the env block of your MCP config and restart. Secrets are never typed into the chat.
The server remembers which APIs you loaded (their spec locations - never credentials or response data) in UCMCP_STATE_FILE and restores them automatically on the next start, so the agent can pick up right where it left off. Set UCMCP_STATE_FILE=off to disable.
Each loaded operation gets an id namespaced as <api>.<operation> (e.g. github.repos_get).
More walkthroughs (weather, GitHub with auth, GraphQL, parallel multi-API workflows, internal APIs): docs/EXAMPLES.md
search_catalog(query="github")
load_api(spec="https://raw.githubusercontent.com/github/rest-api-description/main/descriptions/api.github.com/api.github.com.json", name="github")
search_operations(query="list repositories for user", api="github")
get_operation(operation_id="github.repos_list_for_user")
execute(operation_id="github.repos_list_for_user", params={"username": "torvalds"},
extract=["*.name", "*.stargazers_count"])
GraphQL with field selection:
load_api(spec="https://countries.trevorblades.com/", protocol="graphql", name="countries")
execute(operation_id="countries.country", params={"code": "US", "fields": "name capital currency"})
Chaining (feed one result into the next; wrap steps in a nested list to run them in parallel):
execute_chained(steps=[
{"operation_id": "github.repos_list_for_user", "params": {"username": "torvalds"}, "save_as": "repos"},
{"operation_id": "github.repos_get", "params": {"owner": "torvalds", "repo": "${repos.data.0.name}"},
"extract": ["description", "stargazers_count"]}
])
All settings are environment variables prefixed with UCMCP_:
Credentials are looked up by convention from <API_NAME>_TOKEN, <API_NAME>_API_KEY, <API_NAME>_CLIENT_ID / <API_NAME>_CLIENT_SECRET (OAuth2 client credentials), etc.
pip install -e ".[all,dev]"
pytest # run the test suite
ruff check . # lint
The test suite (60+ tests) and lint run in CI on Ubuntu and Windows with Python 3.10 and 3.12 on every push (.github/workflows/ci.yml); tagging v* builds and publishes to PyPI via trusted publishing (.github/workflows/release.yml).
Contributions welcome - see CONTRIBUTING.md. Security reports go through private reporting.
Releases are automated: tagging v* publishes to PyPI via trusted publishing (see docs/RELEASING.md).
UCMCP_ALLOWED_HOSTS / UCMCP_DENIED_HOSTS.UCMCP_ALLOWED_HOSTS entry.MIT
Security-first MCP server that connects any OpenAPI, GraphQL, gRPC or SOAP API to AI agents.
{ "mcpServers": { "io.github.teodormcp-universal-connector-mcp": { "command": "uvx", "args": [ "universal-connector-mcp==0.2.0" ], "env": { "UCMCP_ALLOWED_HOSTS": "<value>", "UCMCP_APIS_CONFIG": "<value>", "UCMCP_CACHE_TTL": "<value>", "UCMCP_BLOCK_PRIVATE_IPS": "<value>", "GITHUB_TOKEN": "<secret>" } } }}도구
아직 도구 목록이 없습니다. 원격 서버는 첫 상태 확인 후에 도구 목록이 생깁니다.
FAQ
이 페이지에서 Cursor, Claude Desktop, Claude Code 또는 VS Code용 stdio 설정을 복사합니다. PlugMCP 프록시가 아니라 게시자의 설치 방식을 사용합니다.
게시자가 등록한 환경 변수: UCMCP_ALLOWED_HOSTS, UCMCP_APIS_CONFIG, UCMCP_CACHE_TTL, UCMCP_BLOCK_PRIVATE_IPS, GITHUB_TOKEN.
Universal Connector은(는) stdio를 통해 로컬에서 실행됩니다.
마지막 확인: 2026-11-09. Security-first MCP server that connects any OpenAPI, GraphQL, gRPC or SOAP API to AI agents.