Schema | Pinion

Pinion

Describes the environment variables required to run the server.

Name	Required	Description	Default
`GEMINI_API_KEY`	No	API key for Google Gemini (required if provider is gemini).
`GOOGLE_API_KEY`	No	Alternative API key for Google Gemini.
`OPENAI_API_KEY`	No	API key for OpenAI (required if provider is openai).
`PINION_LLM_MODEL`	No	Model name override.
`ANTHROPIC_API_KEY`	No	API key for Anthropic (required if provider is anthropic).
`PINION_MAX_ROUNDS`	No	Max LLM re-synthesis rounds.	3
`PINION_OLLAMA_URL`	No	Ollama server URL (if provider is ollama).	http://localhost:11434
`PINION_GATEWAY_URL`	No	Enterprise gateway URL (required if provider is enterprise-gateway).
`PINION_LLM_PROVIDER`	No	LLM provider. Options: anthropic, openai, gemini, ollama, enterprise-gateway.	anthropic
`PINION_GATEWAY_API_KEY`	No	API key for enterprise gateway (required if provider is enterprise-gateway).
`PINION_SANDBOX_TIMEOUT`	No	Timeout per case in seconds.	5.0
`PINION_DEFAULT_THRESHOLD`	No	Coverage threshold.	0.8
`PINION_SANDBOX_MEMORY_MB`	No	Memory limit per case in MB.	256

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
characterize_functionC	Generate characterization (regression) pytest tests for a single Python pure function. Returns a CharacterizationResult including the emitted pytest code.
characterize_methodA	v2: Generate characterization tests for a single Python class method. Returns a CharacterizationResult including the emitted pytest code with @pytest.fixture-based instance setup.
characterize_moduleA	Generate characterization tests for every pure top-level function in a module. Returns a list of CharacterizationResult, one per function (or per-function error dict). Failures don't abort the whole call.
health_checkA	Check Pinion configuration and LLM provider reachability. When `probe` is False (default), only inspects environment variables and config — no network call. When True, sends a minimal LLM ping.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/namojo/pinion'

If you have feedback or need assistance with the MCP directory API, please join our Discord server