data-ai MCP Server
Git for AI Agent Knowledge. A persistent, versioned memory layer for AI systems. Hybrid GraphRAG retrieval. Runs entirely offline.
Discovered via github-topic:mcp and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
Description
Exact-property match with optional edge traversal. Fast and deterministic - no embedding required.
Add nodes and/or edges as a single commit. Returns the new op-id, commit CID, and created node UUIDs.
Hard-delete: removes the node from the current head commit. Prior commits that referenced it remain addressable. Use only when the goal is to free storage, not memory hygiene.
Walk the op-log from HEAD backwards. Returns the last N operations with time, author, `agent_id`, `task_id`, and message.
Repository overview: op-head, head commit, ref summary, known labels. Cheap; call this first to orient an agent to a new graph.
Raw cosine-similarity nearest-neighbour search over stored node embeddings. Pass a model name and query vector; receive top-k matches.
Same as `mnem_ingest` but writes to the global graph. Use for documents that should be queryable across all sessions and projects.
**Primary retrieval tool.** Hybrid semantic + sparse + graph search. Returns nodes pre-rendered to text plus `tokens_used` / `dropped` / `candidates_seen` metadata. Supports graph-expand, community filter, PPR, and cross-encoder rerank.
Compound write: resolve-or-create a subject node, resolve-or-create an object node, and connect them with a typed edge - all in one call. Prevents the duplicate-entity problem (see example below).
List all named tags (`refs/tags/*`) in the repository.
List all edges pointing to a node (reverse lookup). Equivalent to `mnem blame` in the CLI.
Soft-delete: marks a node as forgotten. Hidden from retrieval by default, but the node CID and all prior commits remain intact for auditing. Use when a user says "forget X" or revokes consent.
Same as `mnem_retrieve` but always targets the global graph (`~/.mnemglobal/.mnem/`). Use for cross-project, cross-session memory.
Inspect node labels and edge predicates in the current commit. Use before writing queries or traversals to discover what's in the graph.
Fetch a single node by UUID. Returns full props, content size, and outgoing edge count.
Write nodes and/or edges directly to the global graph. Use for shared entities (people, orgs, conventions) that appear across multiple projects.
MIT
Enumerate nodes at the current head, optionally filtered by label. Returns UUID + label + summary per node.
From a start node, list outgoing neighbours reachable via specified edge labels.
Find-or-create a node by a primary-key property. If a matching `(label, anchor-property) == value` exists, its UUID is returned; otherwise a new node is committed.
Extractive Centroid + MMR (Maximal Marginal Relevance, diversity-promoting selection) summarizer over a caller-supplied set of node UUIDs. No LLM call - picks `k` sentences balancing proximity to the community centroid against diversity. Enabled via the `summarize` cargo feature.
Ingest a file path or inline text as a `Doc + Chunk + Entity` subgraph. Accepts `{path: "notes.md"}` or `{text: "...", source: "label"}`. Chunker options: `auto`, `paragraph`, `recursive`, `sentence_recursive`, `session`, `structural`.
Same as `mnem_tombstone_node` but operates on the global graph.
BM25 + SPLADE keyword scoring, fused with vector results. Enabled by `[sparse]` block in `config.toml`.
500 Q hybrid-v4
mnem
250 (5x50)
mean retrieve
1986 Q
mnem
highlevel/movie 100
What it does
Flag
cohere
Role