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 skills/daedalus/mcp-external-memory/mcp-external-memorynpx skills add daedalus/mcp-external-memory --skill mcp-external-memorygit clone --depth 1 https://github.com/daedalus/mcp-external-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/skills/daedalus/mcp-external-memory/mcp-external-memory)<a href="https://agentmods.dev/skills/daedalus/mcp-external-memory/mcp-external-memory"><img src="https://agentmods.dev/badge/skills/daedalus/mcp-external-memory/mcp-external-memory.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 | $0.00000 | $0.00196 |
| Opus 5 | $0.00000 | $0.00098 |
| Sonnet 5 | $0.00000 | $0.00039 |
| Haiku 4.5 | $0.00000 | $0.00020 |
Grade A, and why
mcp-external-memory 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 External Memory
MCP server that gives LLMs persistent, searchable semantic memory.
When to use this skill
Use this skill when you need to:
- Store information that persists across sessions
- Search semantic memories
- Organize information with namespaces and tags
- Build knowledge bases
Tools
memory_store- Persist text with optional namespace/tagsmemory_search- Semantic search over all memoriesmemory_get- Retrieve a memory by IDmemory_delete- Delete a memory by IDmemory_list- List memories with filtersmemory_stats- Count memories, namespacesmemory_update- Update an existing memory
Embedding Backends
- TF-IDF (default, pure Python)
- OpenAI (text-embedding-3-small)
- Ollama (local embeddings)
Install
pip install mcp-external-memory
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 · 33 lines · 0 tokens per session scan A 1691d1b556a5
mcp-external-memory is a skill published in the GitHub repository daedalus/mcp-external-memory (0 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 196 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 2026-08-31.
Other skills, from other repositories
index-knowledge
Generate hierarchical AGENTS.md knowledge base for a codebase. Creates root + complexity-scored subdirectory documentation.
add-editor
Wire Deus's memory + evolution layers into an external code editor (Zed and other ACP/MCP clients) so the editor's own agent gains Deus's vault recall and self-improving reflexion loop. Configuration only — no new code. Triggers on "add editor", "use Deus in my editor", "zed integration", "editor integration", "wire…
neuron-curated-memory
Use Neuron (the semantic-memory MCP server) the RIGHT way so its graph stays clean and useful. Before answering, load prior context; after answering, save a CURATED turn — 3-5 concept keywords (nouns/entities/tech, never verbs or filler), typed links with a short rationale, and never a self-link. This raises graph…
neuron-usage
Correct-usage playbook for the Neuron semantic memory MCP (neuron tools). Use when storing or recalling memories with Neuron, when deciding what to pass to preturn/storeturn, when the user says "remember this", "salva in memoria", "cosa ricordi di", "usa neuron", when curating keywords/links for the knowledge graph…
learn-procedure
Capture a repeatable task procedure from the just-completed work as a durable, queryable memory node, so the steps are recalled automatically next time instead of re-derived. Triggers on "learn this procedure", "remember how to do this", "save this as a procedure", "/learn-procedure".
learn-this
Teach the user a topic and persist what they learn as queryable vault memory, grounded in NotebookLM. Vault-native companion to /teach.