Verifiable agent memory with signed ledger receipts — verify every write offline.
Verifiable agent memory with signed ledger receipts — verify every write offline. Exposed over MCP by the acta — verifiable agent memory mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
This repository is the distribution surface for the acta-mcp MCP server binary. All source code, CI pipelines, and reproducible builds live in the acta monorepo. This repo holds the standalone artifact releases and documentation.
Everything the assistant can do here goes through one of these:
acta_write_intent — Store a standing or task intentacta_write_claim — Append a signed subject→predicate→object claimacta_commit_memory — Store a note/observation/document chunkacta_read_context — Compile a signed context bundle (intents + claims + memory)acta_get_state_root — Current signed ledger state rootacta_verify — Verify the full ledger chain offlineacta_answer_lookup — Check the verifiable answer cache before expensive workacta_answer_put — Memoize a final answer with a signed provenance receiptTools — The authoritative tool registry is [api/mcp-tool-registry-v1.json](https://github.com/Kylewilson04/acta/blob/main/crates/acta-mcp/api/mcp-tool-registrVerification — The Verification tool exposed by this serverYou will need 3 environment variables: ACTA_URL, ACTA_TENANT, ACTA_API_KEY. 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.
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Acta — Verifiable Agent Memory's toolset — acta_write_intent, acta_write_claim, acta_commit_memory and 7 more — is a fair guide to whether it matches your workflow. It is maintained by Kylewilson04; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| acta_write_intent | Store a standing or task intent |
| acta_write_claim | Append a signed subject→predicate→object claim |
| acta_commit_memory | Store a note/observation/document chunk |
| acta_read_context | Compile a signed context bundle (intents + claims + memory) |
| acta_get_state_root | Current signed ledger state root |
| acta_verify | Verify the full ledger chain offline |
| acta_answer_lookup | Check the verifiable answer cache before expensive work |
| acta_answer_put | Memoize a final answer with a signed provenance receipt |
| Tools | The authoritative tool registry is [api/mcp-tool-registry-v1.json](https://github.com/Kylewilson04/acta/blob/main/crates/acta-mcp/api/mcp-tool-registry-v1.json) in the monorepo. |
| Verification | The Verification tool exposed by this server. |
{
"mcpServers": {
"acta": {
"command": "/path/to/acta-mcp",
"env": {
"ACTA_URL": "http://localhost:8088",
"ACTA_TENANT": "my-agent"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| ACTA_URL | Endpoint or connection string the server talks to. | Yes |
| ACTA_TENANT | Configuration value read at startup. | Optional |
| ACTA_API_KEY | Credential the server authenticates with. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.