Mnemograph

Event-sourced knowledge graph memory for AI coding agents with semantic search

Connector by tm42 · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 2

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/tm42-mnemograph

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Event-sourced knowledge graph memory for AI coding agents with semantic search

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 15 read · 12 write · 4 delete · 3 not yet classified
Secrets: None asked for
Install scripts: Not scanned yet
Runs as: Python package

Tools by what they do 34

Read from the source code; the running server may list different tools.

Read 15 · Look things up without changing anything.

branch_current
branch_diff
branch_list
diff_timerange
find_orphans
find_similar
get_entity_history
get_graph_health
get_primer
get_relation_weight
get_state_at
get_strongest_connections

Show 3 more tools

get_weak_relations
recall
suggest_relations

Write 12 · Create, change, send or run things.

add_observations
branch_add
branch_checkout
branch_create
create_entities
create_entities_force
create_relations
merge_entities
remember
restore_state_at
session_start
set_relation_importance

Delete 4 · Delete, drop, revoke or wipe things.

clear_graph
delete_entities
delete_observations
delete_relations

Not yet classified 3 · We could not tell from the name and description.

reload
rewind
session_end

Secrets and settings it asks for

Other settings (environment variables or headers).

MEMORY_PATH

Files it touches

Any path the agent passes to its tools

Tools (34)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

add_observations
Add atomic facts to existing entities. One fact per observation — don't dump paragraphs. Use prefixes: 'Gotcha: ...', 'Warning: ...', 'Status: ...', 'Source: ...'. For relations, use create_relations instead of 'X is related to Y' observations.
branch_add
Add entities to the current branch. Only works on non-main branches. Optionally includes relations between added entities.
branch_checkout
Switch to a different branch. Changes what entities/relations are visible in queries. Use 'main' to see everything.
branch_create
Create a new branch with seed entities. Uses BFS to expand from seeds to N-hop neighbors. Branch names follow format: <type>/<name> where type is project|feature|domain|spike|archive.
branch_current
Get the name and details of the currently active branch.
branch_diff
Show differences between two branches. Returns entities and relations that are only in one branch vs the other, plus what's common to both.
branch_list
List all memory branches. Branches are filtered views of the knowledge graph. Main branch sees everything; other branches see filtered subsets.
clear_graph
Clear ALL entities and relations from the graph. Use sparingly! For graphs with >10 entities: requires reason AND confirm_token. Event-sourced: can rewind to before clear with get_state_at(timestamp).
create_entities
Create new entities in the knowledge graph. AUTO-BLOCKS if similar entity exists (>80% match) — returns warning with suggestion. Use create_entities_force to override. Types: concept, decision, project, pattern, question, learning. Naming: use canonical names ('Python' not 'python language'), prefix decisions ('Decision: Use Redis').
create_entities_force
Create entities BYPASSING duplicate check. Use when you're certain the entity is distinct despite similar names (e.g., 'React' library vs 'React' conference).
create_relations
Create relations (edges) between entities. Every entity should have at least one relation. Use specific types: uses, implements, part_of, depends_on, alternative_to, decided_by, affects. Avoid generic 'related_to' when a specific type fits.
delete_entities
Delete entities by name (cascades to relations)
delete_observations
Delete specific observations from entities
delete_relations
Delete specific relations
diff_timerange
Show what changed between two points in time

Show 19 more tools

find_orphans
Find entities with no relations (likely incomplete). Orphans should be connected, merged into another entity, or deleted.
find_similar
Find entities with similar names (potential duplicates). Use before creating to check for existing entities. Returns similarity scores — consider merging if >0.85.
get_entity_history
Get the history of all changes to an entity
get_graph_health
Assess knowledge graph quality. Returns: orphan count, potential duplicates, overloaded entities, weak relations. Run periodically to maintain graph hygiene. Use full=true for deep duplicate detection (slower).
get_primer
Get oriented with this knowledge graph. Call at session start.
get_relation_weight
Get weight breakdown for a relation (recency, co-access, explicit)
get_state_at
Get graph state at a specific point in time (event rewind)
get_strongest_connections
Get an entity's strongest connections by edge weight
get_weak_relations
Get relations below a weight threshold (pruning candidates)
merge_entities
Merge source entity into target. Source's observations and relations move to target, then source is deleted. Use to consolidate duplicates (e.g., merge 'ReactJS' into 'React').
recall
PRIMARY RETRIEVAL TOOL. Get relevant context with automatic token management. Use focus=['EntityName'] to get full details on specific entities. shallow=quick summary, medium=semantic search+neighbors, deep=full exploration.
reload
Reload graph state from mnemograph.db on disk. Use after: git operations (checkout, restore), external edits to mnemograph.db, or any time MCP server seems out of sync.
remember
Store knowledge atomically — entity + observations + relations in ONE call. PRIMARY TOOL for storing new knowledge. Prevents orphan entities. AUTO-BLOCKS if similar entity exists (>80% match). Use force=True to override.
restore_state_at
Restore graph to state at a specific timestamp. Emits clear + recreate events — full audit trail preserved. Use get_state_at() first to preview what will be restored.
rewind
Rewind graph to a previous state using git. Fast undo, audit trail in git only. For audit-preserving restore, use restore_state_at() instead.
session_end
Signal session end, optionally save summary
session_start
Signal session start and get initial context. Returns quick_start guide with tool usage. IMPORTANT: If memory is empty, ask user whether to use project-local or global memory scope.
set_relation_importance
Set explicit importance weight for a relation
suggest_relations
Suggest potential relations for an entity based on semantic similarity and co-occurrence. Useful for connecting newly created entities or discovering missing links.

Signals

Stars: 2
Forks: 0
Open issues: 0
Weekly downloads: 93
Last commit: Feb 14, 2026 (8 months ago)
Last release: Feb 14, 2026 (8 months ago)
Last package publish: Feb 14, 2026 (8 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.tm42/mnemograph
Version: 0.5.1
Auth: No auth
Packages: pypi mnemograph
License: MIT
Repository: github.com/tm42/mnemograph
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql

Cite this page

Mnemograph MCP server. Agent Mart. https://agentmart.dev/connectors/tm42-mnemograph (last updated 2026-10-24)