context-lattice
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| memory_searchA | Search durable coding-agent memory and return bounded, untrusted, cited evidence. |
| memory_getB | Resolve one Context Lattice citation and verify it against its original source file. |
| memory_explainC | Search memory and include deterministic routing, fusion, and abstention diagnostics. |
| memory_syncB | Incrementally ingest allowed agent-session roots and atomically update affected indexes. |
| memory_statusA | Report corpus, schema, index model, and allowed-source health without message content. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
The tools are mostly distinct in purpose: search returns evidence, get resolves a specific citation, explain adds diagnostics, sync ingests data, and status reports health. The only meaningful overlap is between memory_search and memory_explain, since both perform searches, but their different outputs make the distinction usable.
All tools share the consistent memory_ prefix and lower_snake_case convention. The minor deviation is memory_status, which names a state rather than an action, while the other four tools use memory_ followed by a verb-like operation.
Five tools is a well-scoped number for a memory/context server. Each tool covers a distinct part of the workflow: search, resolution, explanation, sync, and status.
The surface covers the core memory lifecycle: retrieval, verification, diagnostics, ingestion, and health monitoring. There is no explicit delete/forget or curation operation, but this is a minor gap because memory appears to be source-backed and managed through the sync tool.