GitHub - knowsuchagency/mcp2cli: Turn any MCP, OpenAPI, or GraphQL server into a CLI — at runtime, with zero codegen

Turn any MCP server, OpenAPI spec, or GraphQL endpoint into a CLI — at runtime, with zero codegen.
Save 96–99% of the tokens wasted on tool schemas every turn.

Read the full writeup →

Install

# Run directly without installing
uvx mcp2cli --help

# Or install globally
uv tool install mcp2cli

AI Agent Skill

mcp2cli ships with an installable skill that teaches AI coding agents (Claude Code, Cursor, Codex) how to use it. Once installed, your agent can discover and call any MCP server or OpenAPI endpoint — and even generate new skills from APIs.

npx skills add knowsuchagency/mcp2cli --skill mcp2cli

After installing, try prompts like:

mcp2cli --mcp https://mcp.example.com/sse — interact with an MCP server
mcp2cli create a skill for https://api.example.com/openapi.json — generate a skill from an API

Usage

MCP HTTP/SSE mode

# Connect to an MCP server over HTTP
mcp2cli --mcp https://mcp.example.com/sse --list

# Call a tool
mcp2cli --mcp https://mcp.example.com/sse search --query "test"

# With auth header
mcp2cli --mcp https://mcp.example.com/sse --auth-header "x-api-key:sk-..." \
  query --sql "SELECT 1"

# Force a specific transport (skip streamable HTTP fallback dance)
mcp2cli --mcp https://mcp.example.com/sse --transport sse --list

# Search tools by name or description (case-insensitive substring match)
mcp2cli --mcp https://mcp.example.com/sse --search "task"

--search implies --list and works across all modes (--mcp, --spec, --graphql, --mcp-stdio).

OAuth authentication

APIs that require OAuth are supported out of the box — across MCP, OpenAPI, and GraphQL modes. mcp2cli handles token acquisition, caching, and refresh automatically.

# Authorization code + PKCE flow (opens browser for login)
mcp2cli --mcp https://mcp.example.com/sse --oauth --list
mcp2cli --spec https://api.example.com/openapi.json --oauth --list
mcp2cli --graphql https://api.example.com/graphql --oauth --list

# Client credentials flow (machine-to-machine, no browser)
mcp2cli --spec https://api.example.com/openapi.json \
  --oauth-client-id "my-client-id" \
  --oauth-client-secret "my-secret" \
  list-pets

# With specific scopes
mcp2cli --graphql https://api.example.com/graphql --oauth --oauth-scope "read write" users

# Local spec file — use --base-url for OAuth discovery
mcp2cli --spec ./openapi.json --base-url https://api.example.com --oauth --list

Tokens are persisted in ~/.cache/mcp2cli/oauth/ so subsequent calls reuse existing tokens and refresh automatically when they expire.

Secrets from environment or files

Sensitive values (--auth-header values, --oauth-client-id, --oauth-client-secret) support env: and file: prefixes to avoid passing secrets as CLI arguments (which are visible in process listings):

# Read from environment variable
mcp2cli --mcp https://mcp.example.com/sse \
  --auth-header "Authorization:env:MY_API_TOKEN" \
  --list

# Read from file
mcp2cli --mcp https://mcp.example.com/sse \
  --oauth-client-secret "file:/run/secrets/client_secret" \
  --oauth-client-id "my-client-id" \
  --list

# Works with secret managers that inject env vars
fnox exec -- mcp2cli --mcp https://mcp.example.com/sse \
  --oauth-client-id "env:OAUTH_CLIENT_ID" \
  --oauth-client-secret "env:OAUTH_CLIENT_SECRET" \
  --list

MCP stdio mode

# List tools from an MCP server
mcp2cli --mcp-stdio "npx @modelcontextprotocol/server-filesystem /tmp" --list

# Call a tool
mcp2cli --mcp-stdio "npx @modelcontextprotocol/server-filesystem /tmp" \
  read-file --path /tmp/hello.txt

# Pass environment variables to the server process
mcp2cli --mcp-stdio "node server.js" --env API_KEY=sk-... --env DEBUG=1 \
  search --query "test"

OpenAPI mode

# List all commands from a remote spec
mcp2cli --spec https://petstore3.swagger.io/api/v3/openapi.json --list

# Call an endpoint
mcp2cli --spec ./openapi.json --base-url https://api.example.com list-pets --status available

# With auth
mcp2cli --spec ./spec.json --auth-header "Authorization:Bearer tok_..." create-item --name "Test"

# POST with JSON body from stdin
echo '{"name": "Fido", "tag": "dog"}' | mcp2cli --spec ./spec.json create-pet --stdin

# Local YAML spec
mcp2cli --spec ./api.yaml --base-url http://localhost:8000 --list

GraphQL mode

# List all queries and mutations from a GraphQL endpoint
mcp2cli --graphql https://api.example.com/graphql --list

# Call a query
mcp2cli --graphql https://api.example.com/graphql users --limit 10

# Call a mutation
mcp2cli --graphql https://api.example.com/graphql create-user --name "Alice" --email "alice@example.com"

# Override auto-generated selection set fields
mcp2cli --graphql https://api.example.com/graphql users --fields "id name email"

# With auth
mcp2cli --graphql https://api.example.com/graphql --auth-header "Authorization:Bearer tok_..." users

mcp2cli introspects the endpoint, discovers queries and mutations, auto-generates selection sets, and constructs parameterized queries with proper variable declarations. No SDL parsing, no code generation — just point and run.

Bake mode — save connection settings

Tired of repeating --spec/--mcp/--mcp-stdio plus auth flags on every invocation? Bake them into a named configuration:

# Create a baked tool from an OpenAPI spec
mcp2cli bake create petstore --spec https://api.example.com/spec.json \
  --exclude "delete-*,update-*" --methods GET,POST --cache-ttl 7200

# Create a baked tool from an MCP stdio server
mcp2cli bake create mygit --mcp-stdio "npx @mcp/github" \
  --include "search-*,list-*" --exclude "delete-*"

# Use a baked tool with @ prefix — no connection flags needed
mcp2cli @petstore --list
mcp2cli @petstore list-pets --limit 10
mcp2cli @mygit search-repos --query "rust"

# Manage baked tools
mcp2cli bake list                         # show all baked tools
mcp2cli bake show petstore                # show config (secrets masked)
mcp2cli bake update petstore --cache-ttl 3600
mcp2cli bake remove petstore
mcp2cli bake install petstore             # creates ~/.local/bin/petstore wrapper
mcp2cli bake install petstore --dir ./scripts/  # install wrapper to custom directory

Filtering options:

--include — comma-separated glob patterns to whitelist tools (e.g. "list-*,get-*")
--exclude — comma-separated glob patterns to blacklist tools (e.g. "delete-*")
--methods — comma-separated HTTP methods to allow (e.g. "GET,POST", OpenAPI only)

Configs are stored in ~/.config/mcp2cli/baked.json. Override with MCP2CLI_CONFIG_DIR.

Output control

# Pretty-print JSON (also auto-enabled for TTY)
mcp2cli --spec ./spec.json --pretty list-pets

# Raw response body (no JSON parsing)
mcp2cli --spec ./spec.json --raw get-data

# Filter JSON with jq (preferred over Python for JSON processing)
mcp2cli --spec ./spec.json list-pets --jq '.[].name'
mcp2cli --spec ./spec.json list-pets --jq '[.[] | select(.status == "available")] | length'

# Truncate large responses to first N records
mcp2cli --spec ./spec.json list-records --head 5
mcp2cli --spec ./spec.json list-records --head 3 --jq '.'  # preview then filter

# Pipe-friendly (compact JSON when not a TTY)
mcp2cli --spec ./spec.json list-pets | jq '.[] | .name'

# TOON output — token-efficient encoding for LLM consumption
# Best for large uniform arrays (40-60% fewer tokens than JSON)
mcp2cli --mcp https://mcp.example.com/sse --toon list-tags

Caching

Specs and MCP tool lists are cached in ~/.cache/mcp2cli/ with a 1-hour TTL by default.

# Force refresh
mcp2cli --spec https://api.example.com/spec.json --refresh --list

# Custom TTL (seconds)
mcp2cli --spec https://api.example.com/spec.json --cache-ttl 86400 --list

# Custom cache key
mcp2cli --spec https://api.example.com/spec.json --cache-key my-api --list

# Override cache directory
MCP2CLI_CACHE_DIR=/tmp/my-cache mcp2cli --spec ./spec.json --list

Local file specs are never cached.

CLI reference

mcp2cli [global options] <subcommand> [command options]

Source (mutually exclusive, one required):
  --spec URL|FILE       OpenAPI spec (JSON or YAML, local or remote)
  --mcp URL             MCP server URL (HTTP/SSE)
  --mcp-stdio CMD       MCP server command (stdio transport)
  --graphql URL         GraphQL endpoint URL

Options:
  --auth-header K:V       HTTP header (repeatable, value supports env:/file: prefixes)
  --base-url URL          Override base URL from spec
  --transport TYPE        MCP HTTP transport: auto|sse|streamable (default: auto)
  --env KEY=VALUE         Env var for MCP stdio server (repeatable)
  --oauth                 Enable OAuth (authorization code + PKCE flow)
  --oauth-client-id ID    OAuth client ID (supports env:/file: prefixes)
  --oauth-client-secret S OAuth client secret (supports env:/file: prefixes)
  --oauth-scope SCOPE     OAuth scope(s) to request
  --cache-key KEY         Custom cache key
  --cache-ttl SECONDS     Cache TTL (default: 3600)
  --refresh               Bypass cache
  --list                  List available subcommands
  --search PATTERN        Search tools by name or description (implies --list)
  --fields FIELDS         Override GraphQL selection set (e.g. "id name email")
  --pretty                Pretty-print JSON output
  --raw                   Print raw response body
  --toon                  Encode output as TOON (token-efficient for LLMs)
  --jq EXPR               Filter JSON output through jq expression
  --head N                Limit output to first N records (arrays)
  --version               Show version

Bake mode:
  bake create NAME [opts]   Save connection settings as a named tool
  bake list                 List all baked tools
  bake show NAME            Show config (secrets masked)
  bake update NAME [opts]   Update a baked tool
  bake remove NAME          Delete a baked tool
  bake install NAME         Create ~/.local/bin wrapper script
  @NAME [args]              Run a baked tool (e.g. mcp2cli @petstore --list)

Subcommands and their flags are generated dynamically from the spec or MCP server tool definitions. Run <subcommand> --help for details.

For token savings analysis, architecture details, and comparison to Anthropic's Tool Search, see the full writeup on the OCAI blog.

Development

# Install with test + MCP deps
uv sync --extra test

# Run tests (96 tests covering OpenAPI, MCP stdio, MCP HTTP, caching, and token savings)
uv run pytest tests/ -v

# Run just the token savings tests
uv run pytest tests/test_token_savings.py -v -s

License

MIT

_{mcp2cli builds on ideas from CLIHub by Kagan Yilmaz (CLI-based tool access for token efficiency)}