ChainMemory MCP server

ChainMemory MCP Server

Cross-model, cryptographically verifiable memory for Claude, ChatGPT, and any AI agent — own your AI's memory and carry it across every model.

ChainMemory MCP exposes the ChainMemory protocol to any AI agent that speaks the Model Context Protocol. Memories are encrypted (AES-256-GCM), anchored on-chain one by one so anyone can verify them, and portable across ChatGPT, Claude, Gemini, Perplexity, and any other LLM. No vendor lock-in, ever.

What's new in v2.7.1

2.5.6 to every client, whatever package was installed. It now reads the version from package.json, so the two cannot drift again.

• Correct version in the MCP handshake. The server announced itself as

side (2026-09-14), no client change needed. Before, it listed memories it had found as not found and told the agent to fix a list that was fine.

• quoteinject reports missing memories correctly** — fixed on the API

each injected memory.

• getinjecthistory responses now include memory_numbers, the #N of

What's new in v2.7.0

Tool descriptions rewritten for agents, not for humans. An audit of all 36 found that only 39% said when to use them, 25% stated their limits, and two charged without saying so. One of them was plainly wrong.

registration block. None of those fields exist — the API returns chainmemories, localmemories, syncedmemories, pendingsync, reputation, owner and active. The v2.5.6 release fixed the code that asked for the wrong fields; the description kept advertising them.

• chainmemory_profile promised memory count, trust score and

(0.05 + 0.005 per op) now state their fee. They are the most used and the most expensive tool respectively.

• chainmemoryremember (0.001 AIC) and updateproject_state

low, med or high — not medium, not critical. A wrong value costs a rejected op and the fee is charged anyway.

• updateprojectstate now documents the closed value sets. severity is

start". Now each says when to use it instead of the other.

• getmycontext and chainmemory_recall both said "use at conversation

that cost a failed call: deleteproject needs the numeric id and rejects the slug; addprojectfromtemplate and listprojecttemplates deal in ids that cannot be guessed; chainmemory_seal is the only tool requiring a wallet private key.

• Twelve one-line descriptions gained their cost, their limits and the gotchas

No behaviour changed: same 36 tools, same endpoints, same fees. What changed is what the agent is told before it chooses.

What's new in v2.6.1

Documentation fix only, no code changes. The blind vault section described the verification step wrongly: GET /v1/memory//decrypted does not fail on a sealed memory — it returns 200 with scheme: "sealed" and the encrypted blob. The guarantee is the same (the operator never gets your text) but the observed behaviour was not what we documented. Found by running the first end-to-end test against the live API.

What's new in v2.6.0

Blind vault — memories the server cannot read. Pass sealed: true to chainmemory_remember and the text is encrypted on your own machine before it leaves: AES-256-GCM with a key derived from twelve BIP-39 words that never touch the network. ChainMemory stores an opaque blob and anchors its hash. Same fee as a normal write — privacy costs nothing extra.

Shortened. The full README is on GitHub.