Connection check
local install
contextengine
MCP server — AI agents that remember across sessions. Zero API keys, 100% local.
Tools
22
GitHub stars
3
Installs / wk
126
Licence
—
Transport
stdio
Last checked
never
Tools & capabilities
22 toolsRead from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.
activate
from source
Activate a ContextEngine Pro license to unlock premium tools (score_project, run_audit, check_ports, list_projects, HTML reports). Get a license at https://api.compr.ch/contextengi… Activate a ContextEngine Pro license to unlock premium tools (score_project, run_audit, check_ports, list_projects, HTML reports). Get a license at https://api.compr.ch/contextengine/pricing
activation_status
from source
Check current ContextEngine license status, plan, and available premium tools. Check current ContextEngine license status, plan, and available premium tools.
agent_cost
from source
Multi-agent cost report from Claude Code Multi-agent cost report from Claude Code
audit_verify
from source
check_ports
from source
Scan all projects for port declarations (ecosystem.config.js, docker-compose.yml, .env, package.json) and detect port conflicts. Returns a port allocation map with conflict warning… Scan all projects for port declarations (ecosystem.config.js, docker-compose.yml, .env, package.json) and detect port conflicts. Returns a port allocation map with conflict warnings. Requires Pro license.
delete_learning
from source
Delete a learning by its ID. Use list_learnings first to find the ID of the learning you want to remove. Delete a learning by its ID. Use list_learnings first to find the ID of the learning you want to remove.
delete_session
from source
Delete a saved session by name. Returns success/not-found. Use for cleanup of stale or obsolete session context. Delete a saved session by name. Returns success/not-found. Use for cleanup of stale or obsolete session context.
drift_status
from source
Returns active drift / loop / stuck-tool / fabrication / silent-failure signals detected over the recent audit-log window. Use to self-check before starting a major task phase. If… Returns active drift / loop / stuck-tool / fabrication / silent-failure signals detected over the recent audit-log window. Use to self-check before starting a major task phase. If any
end_session
from source
MUST be called before ending any coding session. Checks all project repos for uncommitted changes, verifies documentation freshness (copilot-instructions.md, SKILLS.md, session doc… MUST be called before ending any coding session. Checks all project repos for uncommitted changes, verifies documentation freshness (copilot-instructions.md, SKILLS.md, session docs), and returns a checklist of required actions. Will report PASS/FAIL for each check. The AI agent should resolve all FAIL items before ending.
import_learnings
from source
Bulk-import learnings from a Markdown or JSON file. Parses headings, bullets, and tables to extract operational rules. Supports: (1) Structured Markdown (H2=category, H3=rule, bull… Bulk-import learnings from a Markdown or JSON file. Parses headings, bullets, and tables to extract operational rules. Supports: (1) Structured Markdown (H2=category, H3=rule, bullets=context), (2) Inline bullets with [category] prefix, (3) JSON arrays of {category, rule, context}. Deduplicates against existing learnings.
list_learnings
from source
List all permanent learnings, optionally filtered by category. Shows operational rules that have been discovered across sessions. Use search_context to find learnings by keyword —… List all permanent learnings, optionally filtered by category. Shows operational rules that have been discovered across sessions. Use search_context to find learnings by keyword — they
list_projects
from source
Discover and analyze all projects in the workspace. Shows tech stack (framework, runtime, key dependencies), infrastructure (git, docker, pm2), and git remote status for each proje… Discover and analyze all projects in the workspace. Shows tech stack (framework, runtime, key dependencies), infrastructure (git, docker, pm2), and git remote status for each project. Requires Pro license.
list_sessions
from source
List all saved sessions. Shows session names, entry counts, and timestamps. Use to discover what context is available from previous conversations. List all saved sessions. Shows session names, entry counts, and timestamps. Use to discover what context is available from previous conversations.
list_sources
from source
List all knowledge sources indexed by ContextEngine, with their status (found/missing) and chunk counts. List all knowledge sources indexed by ContextEngine, with their status (found/missing) and chunk counts.
load_session
from source
Load a previously saved session by name. Returns all stored key-value entries with timestamps. Use at the start of a session to restore context from a previous conversation. Load a previously saved session by name. Returns all stored key-value entries with timestamps. Use at the start of a session to restore context from a previous conversation.
read_source
from source
Read the full content of a specific knowledge source by name. Read the full content of a specific knowledge source by name.
reindex
from source
Force a full re-index of all knowledge sources. Use after adding new files or changing contextengine.json. Force a full re-index of all knowledge sources. Use after adding new files or changing contextengine.json.
run_audit
from source
save_learning
from source
Save a permanent operational rule learned during a coding session. Unlike sessions (ephemeral), learnings persist forever and auto-surface in search_context results so AI agents do… Save a permanent operational rule learned during a coding session. Unlike sessions (ephemeral), learnings persist forever and auto-surface in search_context results so AI agents don
save_session
from source
Save a key-value entry to a named session. Use to persist decisions, context, plans, and findings between coding sessions. Each session can hold multiple keys (e.g., Save a key-value entry to a named session. Use to persist decisions, context, plans, and findings between coding sessions. Each session can hold multiple keys (e.g.,
score_project
from source
Score one or all projects on AI-readiness (0-100%). Checks documentation (copilot-instructions, README, CLAUDE.md, .cursorrules, SKILLS.md, .env.example), infrastructure (git, hook… Score one or all projects on AI-readiness (0-100%). Checks documentation (copilot-instructions, README, CLAUDE.md, .cursorrules, SKILLS.md, .env.example), infrastructure (git, hooks, Docker, CI, deploy scripts, PM2), code quality (tests, TypeScript, linting, npm scripts), and security (.env gitignored, secrets exposure, lockfiles). Returns letter grade (A+ to F) with detailed breakdown.
search_context
from source