Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-anythingllm what do the docs say about the deployment process?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server (stdio) that gives Hermes access to the knowledge base in AnythingLLM: documents uploaded through the AnythingLLM web UI (PDF, Word, web pages, Markdown …), organised in workspaces.
Typical setup: AnythingLLM runs as a container on the harness server (loopback port 3001), LLM and embedding model come from an OpenAI-compatible LLM server. This MCP server only talks to AnythingLLM's developer API.
Tool | What it does |
| Lists the workspaces (name, slug). |
| Best passages (text, document title, workspace, score 0..1); all workspaces when |
| Answer from the documents only (chat mode |
| Lists the documents: source path, title, workspaces, last update. |
| The whole text of one document (needs |
| Saves a new note and embeds it; |
| Replaces one passage that occurs exactly once (e.g. ticks off a line); only the change is sent, the document is then stored like |
| Replaces a document's content (new version is embedded first, then the old one removed); source, title and workspaces stay. |
| Deletes a document from every workspace and the storage. |
Writing tools are meant for explicit requests or a skill's workflow. A document is named by its
source path (or its end, e.g. train-log.md), its title or its storage name.
Related MCP server: mcp-vault-reader
.env)Variable | Default | |
|
| AnythingLLM instance |
| — | Settings → Developer API |
|
| per request (answers come from the local LLM) |
|
| minimum similarity of a passage (unrelated ≈ 0.4–0.53, matches ≈ 0.6–0.75) |
|
| passages per search |
| — | AnythingLLM's |
python3 -m venv venv && venv/bin/pip install -r requirements-dev.txt
venv/bin/python -m pytest # fake API via httpx.MockTransport, no network
venv/bin/pylint src testsInstall the release anywhere (with its own venv and .env) and add it to the profile's
config.yaml:
mcp_servers:
mcp-anythingllm:
command: /path/to/mcp-anythingllm/.venv/bin/python
args: [/path/to/mcp-anythingllm/src/main.py]venv/bin/python scripts/import_wiki.py ~/notes --default Personal --folder Work=Work --dry-runFiles below a folder Work go to the workspace "Work", everything else to "Personal";
missing workspaces are created. Already imported files are skipped on a rerun.
This server cannot be deployed
A searchable knowledge base your assistant reads and writes.
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Personal wiki and memory layer for AI assistants. Persistent, structured memory across sessions.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
