Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
COMPACTION_AUTONoauto-compact on ingest when pressure ≥ nowPct (store mode only) (default: false)
COMPACTION_MODENopassthrough | store (default: passthrough)
COMPACTION_HOOKSNopath to hooks JSON
COMPACTION_LLM_MODELNosummarizer model (default: qwen2.5-coder:14b)
COMPACTION_STATE_DIRNosession + ledger persistence (default: ~/.compaction-mcp/sessions)
COMPACTION_SUMMARIZERNodirect | sampling | auto (default: direct)
COMPACTION_EMBED_MODELNoembeddings model for semantic recall
COMPACTION_LLM_API_KEYNooptional bearer token
COMPACTION_LLM_HEADERSNoJSON of extra request headers
COMPACTION_RECALL_MODENoauto | embed | lexical (default: auto)
COMPACTION_LLM_BASE_URLNoOpenAI-compatible endpoint (default: http://localhost:11434/v1)
COMPACTION_TOKEN_BUDGETNodefault window size when host doesn't declare one (default: 128000)
COMPACTION_ALLOWED_ROOTSNocolon-separated roots for file re-hydration (default: cwd)
COMPACTION_HOOKS_ENABLEDNoset false to disable all hook execution (default: true)
COMPACTION_EMBED_BASE_URLNoOpenAI-compatible /embeddings endpoint (default: = LLM base URL)

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Ink01101011/compaction-mcp'

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