Schema | Compendium

Compendium

Describes the environment variables required to run the server.

Name	Required	Description	Default
`RUST_LOG`	No	Logs on stderr only	compendium=info
`COMPENDIUM_HTTP_BIND`	No	Default HTTP listen address	127.0.0.1:8788
`COMPENDIUM_TOKENIZER`	No	BPE encoding: cl100k_base or o200k_base (real-tokens)	cl100k_base
`COMPENDIUM_LOCAL_LLM_URL`	No	OpenAI-compatible base URL (must be loopback). Enables smart actions.
`COMPENDIUM_CHARS_PER_TOKEN`	No	Heuristic chars divided by tokens (ignored with real-tokens)	4.0
`COMPENDIUM_LOCAL_LLM_MODEL`	No	Model id accepted by the local server	Qwen3-4B-GGUF
`COMPENDIUM_MAX_BLANK_LINES`	No	Blank-line collapse limit	1
`COMPENDIUM_SIGNAL_MIN_CHARS`	No	Bypass compress/summarize below this length (0 disables)	1000
`COMPENDIUM_LOCAL_LLM_API_KEY`	No	Optional bearer token for locked loopback servers
`COMPENDIUM_DEFAULT_MAX_TOKENS`	No	Soft cap for compress	2048
`COMPENDIUM_SIMILARITY_THRESHOLD`	No	Jaccard line-dedupe threshold	0.85
`COMPENDIUM_LOCAL_LLM_TIMEOUT_SECS`	No	HTTP timeout (first model load can be slow)	120

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

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/hocestnonsatis/Compendium'

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