Schema | lockwood-group-observability-mcp

lockwood-group-observability-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`INKWELL_PROVIDER`	No	Embedding provider: 'stub' (offline) or 'real' (HTTP embeddings).	stub
`INKWELL_BUDGET_MS`	No	Per-call latency budget in milliseconds.	150.0
`INKWELL_LOG_LEVEL`	No	Log level: DEBUG/INFO/WARNING/ERROR.	INFO
`INKWELL_MAX_RECORDS`	No	Resource guard: max records per call.	20000
`INKWELL_MAX_CLUSTERS`	No	Cluster cap K (bounds per-record cost).	64
`INKWELL_EMBEDDING_DIM`	No	Embedding dimension.	128
`INKWELL_EMBED_API_KEY`	No	API key for the real embedding provider (used when INKWELL_PROVIDER=real).
`INKWELL_EMBED_ENDPOINT`	No	HTTP endpoint for the real embedding provider (used when INKWELL_PROVIDER=real).
`INKWELL_MAX_MESSAGE_BYTES`	No	Resource guard: max bytes per message.	16384
`INKWELL_SIMILARITY_THRESHOLD`	No	Cosine threshold for joining a cluster.	0.55

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`	{}

Functions exposed to the LLM to take actions

Name	Description
triage_logsA	Cluster a window of log records by semantic similarity and rank the clusters for incident triage. Returns clusters worst-first.

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/J-X0/lockwood-group-observability-mcp'

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