mcp-memory-service is a self-hosted memory backend that lets AI agents store and retrieve shared project context through REST, MCP, OAuth, a command-line interface, and a dashboard. It is intended for agent pipelines and clients such as LangGraph, CrewAI, AutoGen, Claude Desktop, and OpenCode, with support for knowledge graphs and memory consolidation. The catalogue includes skills, agents, commands, instructions, hooks, a setting, an MCP entry, and a plugin for its workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/doobidoo/mcp-memory-service/readmegit clone --depth 1 https://github.com/doobidoo/mcp-memory-serviceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/doobidoo/mcp-memory-service/readme)<a href="https://agentmods.dev/commands/doobidoo/mcp-memory-service/readme"><img src="https://agentmods.dev/badge/commands/doobidoo/mcp-memory-service/readme.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00931 |
| Opus 5 | $0.00000 | $0.00465 |
| Sonnet 5 | $0.00000 | $0.00186 |
| Haiku 4.5 | $0.00000 | $0.00093 |
Grade A, and why
README scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Commands
Custom slash commands for mcp-memory-service development.
Available Commands
/release
Full release cycle automation: list open PRs, merge approved, verify CI, check landing page, bump version, create tag + GitHub release, clean branches, save summary to MCP Memory.
/triage
Security alert triage & remediation: scan Dependabot/CodeQL/secret scanning alerts, classify severity + complexity, create fix branches, implement fixes, open PRs, save patterns to MCP Memory.
/refactor-function (PoC)
Automated function complexity reduction using multi-agent workflow.
Status: Proof of Concept (simulated agents)
Usage:
# Quick test
/refactor-function --dry-run
# Interactive (would work with real agents)
# 1. Select function in editor
# 2. Run: /refactor-function
# 3. Review changes
# 4. Apply if approved
Workflow:
Select Function → Baseline Analysis → Refactor → Validate → Review → Apply
Current Implementation (PoC):
- ✅ CLI interface working
- ✅ Workflow orchestration
- ✅ User confirmation flow
- ⚠️ Simulated agent responses (placeholder)
- ❌ Not yet integrated with real agents (amp-bridge, code-quality-guard)
Next Steps for Production:
- Integrate with Task agent calls
- Read actual file content via Read tool
- Apply changes via Edit tool
- Create commits via Bash tool
- Add Claude Code settings.json hook
Proven Track Record:
- Based on Issue #340 workflow (45.5% complexity reduction)
- 2-3x faster than manual refactoring
- 100% validation success rate
Installation
Commands are located in .claude/commands/ and executable:
# Make executable (already done)
chmod +x .claude/commands/refactor-function
# Test PoC
.claude/commands/refactor-function --dry-run
# With options
.claude/commands/refactor-function --target-complexity 6
Configuration (Future)
Add to Claude Code settings.json:
{
"commands": {
"refactor-function": {
"path": ".claude/commands/refactor-function",
"description": "Reduce function complexity automatically",
"requiresSelection": true,
"agents": ["amp-bridge", "code-quality-guard"]
}
}
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 148 lines · 0 tokens per session scan A fca9b6076313
README is a command published in the GitHub repository doobidoo/mcp-memory-service (1,926 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 931 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
chunkhound-release-notes
Generate release notes for a ChunkHound production release.
review-pr
Review Github Pull Request.
graph
Show visualization-ready graph data with nodes, edges, and clusters for the indexed markdown files.
search
Semantic, lexical, hybrid, and edge search across indexed markdown files.
links
Show outgoing and incoming links originating from a specific markdown file, with optional multi-hop neighborhood traversal.
backlinks
Show files that link TO a specific markdown file (incoming links / backlinks).