Agents need durable memory, and you already maintain one — your graph. The missing piece is access you can trust: an agent should read broadly and
Logseq MCP MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Agents need durable memory, and you already maintain one — your graph. The missing piece is access you can trust: an agent should read broadly and write usefully, but never touch what it shouldn't — and never do anything you can't see.
Once Logseq MCP is connected, these are the calls the assistant has available:
Authentication — The Streamable HTTP transport requires a bearer token: every request must send Authorization: Bearer <LOGSEQ_MCP_HTTP_TOKEN>, or it gets 401. TheFind — The Find tool exposed by this serverGuide — The Guide tool exposed by this serverRead — The Read tool exposed by this serverTasks — The Tasks tool exposed by this serverDynamic — The Dynamic tool exposed by this serverThe server ships on npm as @modelcontextprotocol/inspector, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
You will need 5 environment variables: LOGSEQ_API_TOKEN, LOGSEQ_API_URL, YOUR_TOKEN, LOGSEQ_MCP_HTTP_TOKEN, LOGSEQ_MCP_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.
Plenty of planning and project tracking 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. Logseq MCP's toolset — Authentication, Find, Guide and 3 more — is a fair guide to whether it matches your workflow. It is maintained by dailydaniel; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Logseq MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Authentication | The Streamable HTTP transport **requires** a bearer token: every request must send Authorization: Bearer <LOGSEQ_MCP_HTTP_TOKEN>, or it gets 401. The server refuses to start in this mode without a token set. Note this is |
| Find | The Find tool exposed by this server. |
| Guide | The Guide tool exposed by this server. |
| Read | The Read tool exposed by this server. |
| Tasks | The Tasks tool exposed by this server. |
| Dynamic | The Dynamic tool exposed by this server. |
### Claude Desktop
```json
{
"mcpServers": {
"logseq": {
"command": "uvx",
"args": ["mcp-server-logseq"],
"env": {
"LOGSEQ_API_TOKEN": "<YOUR_TOKEN>",
"LOGSEQ_API_URL": "http://127.0.0.1:12315"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| LOGSEQ_API_TOKEN | Credential the server authenticates with. | Yes |
| LOGSEQ_API_URL | Endpoint or connection string the server talks to. | Yes |
| YOUR_TOKEN | Credential the server authenticates with. | Yes |
| LOGSEQ_MCP_HTTP_TOKEN | Credential the server authenticates with. | Yes |
| LOGSEQ_MCP_HOST | Endpoint or connection string the server talks to. | Optional |
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.