Cpersona MCP Server

Give Claude persistent memory across sessions. Single SQLite file. 29 tools. Zero LLM dependency. The cpersona mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

What it actually does

• Declarative memory — — Individual facts, decisions, instructions stored via store
• Episodic memory — — Conversation summaries archived via archive_episode
• Profile memory — — Accumulated user/project attributes via update_profile
• Cosine similarity (semantic relevance)
• Dynamic time decay (adapts to corpus time range — a 1-year-old corpus and a 1-day-old corpus use different decay curves)
• Recall boost (frequently useful memories surface more easily, with natural fade-out)

Its toolset

Everything the assistant can do here goes through one of these:

• store — Store a message in agent memory
• recall — Recall relevant memories (vector + FTS5 + keyword, RRF merge)
• recall_with_context — Recall with external conversation context (auto-dedup)
• get_contents — Expand recall preview refs (mem: / ep:) to full content
• get_profile — Get current agent profile
• update_profile — Save pre-computed agent profile
• get_operating_context — Read the operator-owned operating context served to every client (read-only; edited on the filesystem)
• archive_episode — Archive conversation episode with summary and keywords
• list_memories — List recent memories
• list_episodes — List archived episodes
• update_memory — Update memory content (rejects if locked)
• lock_memory — Lock memory to prevent deletion/editing

Configuration

You will need 6 environment variables: CPERSONA_DB_PATH, EMBEDDING_MODE, EMBEDDING_HTTP_URL, CPERSONA_AUTH_TOKEN, CPERSONA_EMBEDDING_URL, CPERSONA_HTTP_HOST. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at cpersona on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Cpersona's toolset — store, recall, recall_with_context and 11 more — is a fair guide to whether it matches your workflow. It is maintained by cloto-dev; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Cpersona.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the cpersona mcp server does with a few real requests.