common-context-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONTEXT_MCP_FILE | No | Store file, overriding the project folder. Default is <project>/common-context.json. | |
| CONTEXT_MCP_ENFORCE | No | Set to 0 to turn off Claude Code enforcement at runtime. Unset by default. | |
| CONTEXT_MCP_AGENT_ID | No | Stable identity for this agent (e.g. claude-code-laptop). Default is random per process. | |
| CONTEXT_MCP_NO_HOOKS | No | Do not install Claude Code enforcement hooks in --yes mode. Unset by default. | |
| CONTEXT_MCP_NO_SETUP | No | Skip the setup prompt after a global install. Unset by default. | |
| CONTEXT_MCP_PROJECT_DIR | No | Project folder. Its store is common-context.json inside it. Defaults to the working directory. | |
| CONTEXT_MCP_CLAIM_MINUTES | No | Claim lifetime without renewal. Default is 30. | |
| CONTEXT_MCP_STALE_MINUTES | No | Idle time after which a session is considered dead. Default is 15. | |
| CONTEXT_MCP_MAX_OUTPUT_CHARS | No | Cap on any single tool response. Default is 40000. |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| load_contextA | Start a session and load shared context: other agents' work, recent sessions, failures to avoid. Brief by default. |
| save_contextA | Save a fact, decision or config under a key. This is the checkpoint. Overwriting keeps the old value in history. |
| save_summaryA | Save session summary at end of work. MANDATORY before giving final response. Marks session as complete. |
| save_failureB | Record a failed approach IMMEDIATELY when something doesn't work. |
| record_successA | Record an approach that worked, so future agents prefer it. |
| search_contextA | Search shared context by keyword. Returns short excerpts with ids; use get_audit_trail or load_context detail "full" for more. |
| claim_areaA | Claim a file or area so other agents avoid it. Expires after CONTEXT_MCP_CLAIM_MINUTES (default 30). |
| release_areaB | Release a claimed area. |
| list_claimsA | List all currently active (unexpired) area claims. |
| broadcastB | Broadcast a decision/message to all agents. |
| handoffA | Transfer work to another agent with full context. Records a completed handoff session and a broadcast. |
| get_patternsB | Get learned patterns (what works and what fails). |
| get_audit_trailA | Get the audit trail of sessions, failures and claims (most recent first, capped). |
| resume_sessionA | Take over an interrupted session under this agent. Refuses completed sessions and ones another live agent is using. |
| session_statusB | Store health: size, counts, interrupted sessions, estimated tokens of context. |
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 15 tools
Most tools map to a distinct resource+action, but the write-side has several similar-sounding verbs (save_context, save_summary, save_failure, record_success, broadcast) that require careful reading of descriptions to separate. The read side (load_context, search_context, get_patterns, get_audit_trail, session_status) is mostly clear, though load_context vs resume_session could be confused at a glance.
Strong verb_noun convention dominates (load_context, save_context, claim_area, release_area, get_patterns, get_audit_trail). A few outliers break the pattern: broadcast, handoff, and session_status use bare verbs or noun phrases instead of verb_noun.
15 tools sits at the top of the healthy range and each one maps to a real coordination concern (session lifecycle, memory, claims, handoff, audit). No tool appears redundant or filler.
The surface covers session lifecycle, persistence (facts/failures/successes), search, claims, broadcast, handoff and audit, which is solid for a shared-context server. Minor gaps: no delete/forget/expire operation for saved context, no bulk listing of keys, and no explicit force-release for stale claims.