promem-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONTEXTMCP_DATA_DIR | No | Override the data directory path for storage location. By default, each project stores data in its own `.contextmcp/` directory. | <project-root>/.contextmcp/ |
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 |
|---|---|
| ctx_searchA | Search persistent project context for rules, decisions, conventions, and facts. Use this BEFORE writing code to understand project patterns and avoid inconsistencies. Returns relevant memories within the specified token budget. |
| ctx_getB | Get a specific memory by its ID with full provenance. |
| ctx_saveA | Save a memory, decision, rule, or fact to persistent context. Use this to store technical decisions, project rules, coding conventions, or any important context that should persist across AI coding sessions. |
| ctx_updateC | Update an existing memory. Only provided fields are changed. |
| ctx_deleteC | Delete a memory from persistent context. |
| ctx_projectA | Get current project information: name, language, framework, root, git status. |
| ctx_rulesA | Get all project rules and coding conventions. |
| ctx_decisionsA | Get all technical/architecture decisions with reasoning. |
| ctx_recentC | Get recent memories and latest session summary for continuity between sessions. |
| ctx_gitB | Get Git intelligence: recent commits, changed files, branches, TODOs/FIXMEs. detail can be: summary, commits, files, todos |
| ctx_environmentA | Get environment intelligence: Python version, venv, dependencies, Docker, .env status. |
| ctx_diagnosticsA | Run environment diagnostics: missing env vars, config issues, health checks. |
| ctx_summaryA | Get a compact project context summary for handoff between sessions or agents. Includes project info, key rules, recent decisions, environment status, and latest session. |
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 13 tools
Each tool targets a distinct concern (search, get, save, update, delete, project info, etc.) with clear descriptions, making it easy for an agent to choose the right one. No two tools overlap in purpose.
There is a deep inconsistency: most tools use a 'ctx_' prefix (ctx_search, ctx_get, ctx_save, etc.), but a few tools like 'ctx_git', 'ctx_environment', and 'ctx_diagnostics' do not follow this pattern. Additionally, 'ctx_git''s description includes a confusing 'detail' parameter that is not shown in the tool name, breaking the expected consistency.
13 tools is a reasonable count for a project-context memory server, covering search, CRUD for memories, project info, environment, and session summaries. Each tool has a distinct purpose and earns its place.
The tool set covers core memory operations (CRUD), project info, decisions, rules, environment diagnostics, and session continuity. There are no obvious dead ends for common agent tasks like retrieving, storing, updating, or searching context. Minor gap: no tool for batch operations or listing all memories.