Skip to main content
Glama
navid-kianfar

Claude Memory MCP

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MEMORY_MCP_DATA_DIRNoWhere databases are stored~/.claude-memory-mcp
MEMORY_MCP_DAEMON_HOSTNoDaemon bind address (0.0.0.0 in Docker)127.0.0.1
MEMORY_MCP_DAEMON_PORTNoDaemon port8765
MEMORY_MCP_DAEMON_HOSTNAMENoHostname used in the UI URLclaude-memory-mcp

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
memory_versionA

Get the current version of the Memory MCP server and configuration.

memory_useC

Set the active project. Subsequent tools use it by default.

memory_init_projectA

Initialize a new project namespace (creates DuckDB + registers it).

Pass project_path (the project's source folder) to enable git-synced memory: rules/decisions mirror to /.claude-memory/.

memory_load_from_folderA

Load a project from a local folder.

The project name is taken from the folder's package.json ("name") or the folder name. If the folder already contains a portable .memory-mcp.duckdb it is attached as-is; otherwise the project is created and a CLAUDE.md, if present, is imported into memory. The project is auto-activated.

memory_link_folderA

Bind a project to a source folder for git-synced memory.

Once linked, the project's rules/decisions mirror to a committable /.claude-memory/ snapshot - so memory travels with the code across devices and teammates via git push/pull.

memory_rename_projectC

Rename a project (its display name) and optionally update its description.

memory_list_projectsA

List all registered projects.

memory_project_infoC

Get detailed info for a project.

memory_storeB

Store a new memory with auto-embedding, summary, entity extraction, and TTL.

memory_searchC

Semantic search with composite relevance scoring.

memory_recallC

Recall a specific memory by ID or exact title.

memory_updateC

Update an existing memory. Re-embeds if title/content changed.

memory_deleteB

Soft-delete (archive) or hard-delete a memory.

memory_listC

List memories with filtering, sorting, and pagination.

memory_provenanceC

Get the full audit trail for a memory.

memory_get_rulesB

Get all mandatory and forbidden rules (direct SQL, cached).

memory_add_ruleB

Add a project rule. rule_type is 'mandatory' (always do) or 'forbidden' (never do). The rule is enforced in every future session.

memory_update_ruleC

Update an existing mandatory or forbidden rule by its id.

memory_delete_ruleA

Delete a rule by its id. Soft-deletes (archives) unless hard=True.

memory_add_rule_bulkA

Add one rule to many projects at once.

rule_type is 'mandatory' or 'forbidden'. projects=None adds it to every registered project; otherwise pass a list of project slugs. Lets you push a rule to all your projects without doing it one by one.

memory_list_templatesA

List reusable rule/memory templates that can be applied to new projects.

memory_create_templateA

Create a reusable template - a named set of default rules/memories that can be applied when creating new projects so they need not be re-typed.

memory_add_template_ruleA

Add a rule to a template (by template name). rule_type is 'mandatory' or 'forbidden'.

memory_apply_templateC

Apply a template's rules/memories into a project (by template name).

memory_import_rulesA

Copy selected rules/memories from another project into this one. Use memory_get_rules(source_project) first to get the ids to import.

memory_session_startB

Start a session. Loads rules, last summary, sprint goals, recent decisions.

memory_session_endC

End a session and store its summary.

memory_attach_projectC

Attach an existing project directory. Auto-activates on success.

memory_make_portableC

Move the project's DB into the project directory for git sharing.

memory_syncC

Sync a portable DB after git pull. Auto-activates on success.

memory_exportC

Export all active memories to human-readable .md files.

memory_importC

Import memories from exported .md files.

memory_import_claude_mdA

Import a project's CLAUDE.md into memory as categorized entries.

path is the CLAUDE.md file or the directory containing it. Headings are mapped to categories (rules, architecture, decisions, devops, docs...) and rule sections are split per bullet. When stub_rewrite=True, CLAUDE.md is replaced with a slim pointer at memory MCP (the original is backed up).

memory_model_infoC

Current embedding model + available presets.

memory_set_modelC

Switch embedding model between 'english' and 'multilingual' presets.

memory_reembedC

Re-embed all active memories with the current model.

memory_check_updateA

Check if a newer version of the Memory MCP server is available.

Queries GitHub Releases first, falls back to git commit comparison. Does NOT modify anything - it only reports. Returns step-by-step update instructions when a new version is available.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/navid-kianfar/claude-memory-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server