About graphmind
graphmind is a persistent knowledge graph for agents, developers, and other users who need to record and retrieve facts. It stores named entities, observations, and typed relations in a readable JSON file that can be edited by hand and survives restarts.
Key features
- 01Store entities and observations
- 02Connect entities with typed relations
- 03Search and open graph subsets
- 04Persist the graph in a JSON file
- 05Add and delete graph data
Use cases
- 01Maintain durable agent memory
- 02Record facts and links between entities
- 03Inspect or edit the graph file directly
MCP support
Exposes tools for creating, searching, reading, and deleting graph entities, observations, and relations through an MCP server.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEgraphmind
graphmind is a small, durable memory for agents: a knowledge graph you can build up a fact at a time and query back later. You record entities — people, places, projects, anything with a name — each with a type and a growing list of plain-text observations, and you connect them with typed relations ("Alice — lives_in → Lisbon"). The whole graph lives in one JSON file on disk, so the memory survives restarts and stays readable, diffable, and editable by hand.
There is no database to run and no service to sign up for. The graph file is the product.
Install
npx @reneturcios/graphmind read
Or run the container image:
docker run -i ghcr.io/cloudcorprecords/graphmind
The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead. If you run the container, mount a volume over the working directory if you want the graph file to persist between runs.
Where the graph lives
The store file path comes from the GRAPHMIND_FILE environment
variable and defaults to ./graphmind.json in the current working
directory. The file is loaded when the server (or a CLI command)
starts, and it is rewritten after every change, so what is on disk is
always the full current graph:
{
"entities": [
{ "name": "Alice", "entityType": "person", "observations": ["Lives in Lisbon"] }
],
"relations": [
{ "from": "Alice", "to": "Lisbon", "relationType": "lives_in" }
]
}
CLI
The CLI is a read/inspect face over the same store file the MCP server writes:
# Print the whole graph as JSON
graphmind read
# Print the subgraph matching a search term
graphmind search lisbon
# Point at a specific store file
GRAPHMIND_FILE=~/notes/graph.json graphmind read
graphmind --version
Exit codes: 0 on success, 1 when the store cannot be read or
written, 2 for usage errors.
MCP server
One bin serves both faces. The mcp subcommand starts a stdio MCP
server:
npx -y @reneturcios/graphmind mcp
MCP client configuration:
{
"mcpServers": {
"graphmind": {
"command": "npx",
"args": ["-y", "@reneturcios/graphmind", "mcp"],
"env": { "GRAPHMIND_FILE": "/path/to/graphmind.json" }
}
}
}
Tools
| Tool | Input | What it does |
|---|---|---|
create_entities | entities: array of {name, entityType, observations} | Adds entities whose names are not already taken. Existing names are skipped and the stored entity is left untouched. Returns only the entities actually created. |
create_relations | relations: array of {from, to, relationType} | Adds relations whose exact triple is not already present. Returns only the relations actually created. |
add_observations | observations: array of {entityName, contents} | Appends observation strings to existing entities, skipping strings the entity already has. Returns what was added, per entity. |
delete_entities | entityNames: array of strings | Removes the named entities and every relation that touches any of them. |
delete_observations | deletions: array of {entityName, observations} | Removes the listed observation strings from the named entities. |
delete_relations | relations: array of {from, to, relationType} | Removes relations matching the given exact triples. |
read_graph | (none) | Returns the entire graph: all entities and all relations. |
search_nodes | query: string | Case-insensitive substring search over entity names, types, and observations. Returns the matching entities plus the relations whose endpoints both matched. |
open_nodes | names: array of strings | Returns the named entities plus the relations between them. Unknown names are skipped. |
Behaviour worth knowing
- Names are identity. An entity is its name; creating a second entity with the same name does nothing. Rename by deleting and recreating.
- Relations need real endpoints.
create_relationsrequires both thefromandtoentities to already exist, and fails the whole call if one is missing — no stub entities are invented, so a typo surfaces immediately instead of quietly corrupting the graph. - Observations are a set, in order. Adding a string an entity already carries is a no-op; new strings append in the order given.
- Deletes cascade only from entities. Deleting an entity removes its relations; deleting observations or relations never touches anything else.
Development
npm install
npm run build # tsc -> dist/
npm test # node test runner over test/*.test.ts, no network
npm run dev # run the CLI from source via tsx
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.