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 instructions/onekn8/mcp-memory/claude-mdgit clone --depth 1 https://github.com/oneKn8/mcp-memoryWrote 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/instructions/onekn8/mcp-memory/claude-md)<a href="https://agentmods.dev/instructions/onekn8/mcp-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/onekn8/mcp-memory/claude-md.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 | $0.00349 | $0.00349 |
| Opus 5 | $0.00175 | $0.00175 |
| Sonnet 5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
mcp-memory CLAUDE.md 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 3d 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.
What it actually says
mcp-memory
MCP server for persistent agent memory with semantic search.
Language
Python (3.11+)
Build & Run Commands
- Install:
pip install -e ".[dev]" - Test:
pytest - Lint:
ruff check . - Format:
ruff format . - Type check:
mypy mcp_memory - Run:
python -m mcp_memory.server
Project Structure
mcp_memory/server.py- FastMCP server with tool definitionsmcp_memory/storage.py- ChromaDB wrapper (MemoryStore class)mcp_memory/config.py- Environment variable configurationmcp_memory/models.py- Data models (Memory, RecallResult)tests/- pytest tests
Architecture
- FastMCP 3.0 for MCP protocol (stdio transport)
- ChromaDB PersistentClient for vector storage (cosine similarity)
- One ChromaDB collection per project scope
- Default embedding model: all-MiniLM-L6-v2 (via sentence-transformers, auto-downloaded)
- Data stored at ~/.mcp-memory/ (configurable via MCP_MEMORY_DATA_DIR)
MCP Tools
remember- Store a memory with content, tags, project, importancerecall- Semantic search across stored memoriesforget- Delete memories by ID, project, or tagslist_memories- Browse memories with pagination and stats
Conventions
- All tools return formatted strings
- Tags stored as comma-separated strings in ChromaDB metadata
- Per-project isolation via separate ChromaDB collections
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.
- 3d ago First seen · 46 lines · 349 tokens per session scan A 453509efc775
mcp-memory CLAUDE.md is an instructions file published in the GitHub repository oneKn8/mcp-memory (1 stars, last pushed 5mo ago), licensed MIT. It adds 349 tokens to every session, about $0.0017 per session on Opus 5. 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 2026-08-31.
Other instructions, from other repositories
cognirepo CLAUDE.md
Instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).
openexp CLAUDE.md
Instructions for anthroos/openexp, covering openexp — development instructions, memory protocol (mandatory), before starting any task, after completing a task and when the user shares context.