content

MCP tool from MCP Memory by fellowgeek

(string or object, required): Core information to store.

How to use it

content is exposed by the MCP Memory MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the content tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install MCP Memory

$claude mcp add --scope user memory -- /ABSOLUTE/PATH/TO/run.sh

FULL MCP MEMORY LISTING

Other tools in MCP Memory (16)

concept_type

(string, optional, default: "Agent Memory"): OKF concept type (e.g. Metric, Playbook, Attested Computation).

description

(string, optional): One-line summary.

generated_by

(string, optional): Actor identifier following actor convention (<producer>/<version>, human:<id>, process:<id>).

key

(string, required): Unique identifier or path for the memory (e.g. user/preferences/codingstyle or project/architecture).

limit

(integer, optional, default: 10): Maximum number of results.

namespace

(string, optional, default: "default"): Scope/namespace.

project_root

(string, required): Absolute path to the active project root directory (e.g. /Users/user/Projects/my-app).

query

(string, optional): Keyword search query across keys, frontmatter, and content.

resource

(string, optional): Canonical URI of underlying asset.

sources

(array of objects, optional): Provenance sources [{resource, id, title, author, usagecount, lastmodified}].

stale_after

(string, optional): ISO date (YYYY-MM-DD).

status

(string, optional, default: "stable"): Lifecycle state (draft stable deprecated).

summary

(string, optional): One-sentence description of the milestone achieved.