Krusch Context MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_URL | No | Optional URL for a local Ollama server used for embeddings. Example: OLLAMA_URL="http://127.0.0.1:11434". | http://127.0.0.1:11434 |
| EMBED_MODEL | No | Optional embedding model. Used with OLLAMA_URL, e.g. "snowflake-arctic-embed2", "qwen3-embedding", "nomic-embed-text", or "bge-large"; with OPENROUTER_API_KEY, e.g. "baai/bge-large-en-v1.5" or another compatible 1024-dim OpenRouter embedding model. | |
| STORAGE_MODE | No | Optional storage backend. Defaults to SQLite; set to "postgres" to use PostgreSQL with pgvector for multi-agent/centralized persistence. | sqlite |
| OPENROUTER_API_KEY | No | Optional OpenRouter API key for remote cloud embeddings. Example: OPENROUTER_API_KEY="sk-...". |
Instructions
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.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| krusch_context_retrieveA | Universal context retrieval tool. Pulls active project memories, steering rules, and state briefings respecting token budget limits. |
| krusch_context_rememberB | Unified write API for episodic memory and persistent steering nuggets. Includes automatic near-duplicate detection and provenance tracking. |
| krusch_context_reviseA | Unified knowledge revision API. Supports temporal superseding (updating stale knowledge with lineage) and explicit invalidations (revoking obsolete rules with mandatory reason). |
| krusch_context_nudgeA | Invariant auditor and alignment feedback loop. Checks proposed code diffs or actions against active project invariants, and adjusts rule weights based on developer feedback. |
| krusch_context_healthB | Operational health check, memory counts by closed taxonomy, storage mode, and 30-day TTL decay review. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| session_start | Initialize an agent session by retrieving project state briefing and active invariants. |
| pre_commit | Audit staged changes against active project invariants before commit. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Retrieve (read), remember (write new), nudge (audit), and health (ops) are clearly distinct. The only soft boundary is remember vs revise, since both mutate knowledge, but descriptions differentiate creating new memories from superseding/invalidating existing ones.
All tools share a consistent krusch_context_* namespace with a single descriptive suffix, making the set predictable. Minor deviation: retrieve/remember/revise/nudge are verbs but health is a noun, breaking the verb-based pattern slightly.
Five tools is well-scoped for a context/memory server: one per lifecycle concern (read, write, revise, audit, health). Each tool earns its place with no redundancy or bloat.
The surface covers the core memory lifecycle: retrieval, creation with dedup, temporal revision/invalidation, invariant auditing, and health inspection. Minor gaps remain, such as an explicit forget/delete operation or a targeted memory search/listing tool.