MCP tool reference
Altretta exposes your vault to any MCP client through a small, local endpoint — so your AI can query your notes, follow the graph, and check provenance instead of guessing. This page lists those tools and what each one does, and marks the ones that can change your vault.
You don't call these by hand. Your AI client discovers and calls them for you once connected — connecting is one click. This reference is here so you understand what your model can reach, and can trust what it reports back.
How to read this
- Tools are grouped by purpose: grounded retrieval, graph query, verifiability, consistency, and the tools that change things.
- Every tool is classified read-only or mutating, and the default access level is read-only — a connected client is refused every mutating tool until you explicitly grant read-and-write in the Trust panel. A tool that is not classified is denied, so nothing can ship unclassified.
- Every retrieved passage carries a citation (
source:lines) and a provenance anchor — so what the AI quotes can be traced back to your note and its signed history. - Folder exclusions you set in the Trust panel are applied to these tools: an excluded folder never appears in grounded results, backlinks, the vault map, source listings, or graph queries.
Grounded retrieval
The core of grounded, cited answers: the AI pulls only the passages that bear on your question, each with a citation and a signed anchor.
| Tool | What it does |
|---|---|
aingle_ground | The workhorse. Returns cited passages for a question, a provenance anchor, a groundedness verdict (how well the evidence supports an answer), and an instruction the model must follow when answering. |
aingle_sources | List the ingested source files with their content hashes — the signed provenance registry. Takes no arguments. |
aingle_note_context | The notes semantically related by meaning to a given note, not just those it links to. |
aingle_vault_map | Return a Map & Manual–style map of the vault: hub entry points, topic clusters, orphan notes, and tag indices. |
aingle_backlinks | For a note: its backlinks, its outgoing links, and unlinked mentions of it. |
aingle_ping | Liveness check. Returns pong — useful when wiring up a client. |
Graph query
Query the underlying semantic graph directly — subjects, predicates, triples, patterns, and paths.
| Tool | What it does |
|---|---|
aingle_query_pattern | Query the graph by triple pattern (match subject / predicate / object). |
aingle_sparql | Run a SPARQL query over the graph for precise, structured retrieval. |
aingle_path | Find a path between two nodes — how one idea connects to another. |
aingle_list_subjects | List the subjects (entities) in the graph. |
aingle_list_predicates | List the predicates (relationship types) in the graph. |
aingle_list_triples | List triples (subject–predicate–object facts) in the graph. |
aingle_get_triple | Fetch a specific triple. |
aingle_graph_stats | Return summary statistics about the graph — counts and shape. |
Verifiability & DAG
Inspect Altretta's signed action history and its cryptographic proofs — this is what makes answers checkable rather than merely plausible.
| Tool | What it does |
|---|---|
aingle_dag_history | Return the history of actions recorded in the signed DAG. |
aingle_dag_chain | Walk the hash-linked chain of actions to verify continuity. |
aingle_dag_tips | Return the current tips (latest heads) of the DAG. |
aingle_dag_stats | Return summary statistics about the DAG. |
aingle_dag_action | Fetch a single action by its hash. |
aingle_get_proof | Fetch a cryptographic proof for a fact or record. |
aingle_verify_proof | Verify a proof. An invalid proof comes back as valid: false rather than as an error. |
Consistency
Check whether the vault agrees with itself — surfacing contradictions before they mislead the AI.
| Tool | What it does |
|---|---|
aingle_agent_consistency | Check the consistency of what the AI has asserted against the vault. |
aingle_verify_assertions_batch | Verify a batch of assertions against the graph at once. |
aingle_validate | Validate content against the vault's rules. |
aingle_validate_skill | Validate a skill definition. |
Tools that change things
Every tool in this section is refused under the default read-only access level. They only become callable if you switch a client to read-and-write in the Trust panel.
| Tool | What it does |
|---|---|
aingle_ingest | Ingest content into the vault graph — notes or an entire codebase. |
aingle_create_triple | Add a fact to the semantic graph. |
aingle_batch_insert | Add many facts at once. |
aingle_delete_triple | Remove a triple from the graph by its hash id. |
aingle_dag_prune | Destructive. Drop actions from the signed history according to a retention policy, and report how many were pruned. |
aingle_sandbox_create | Create a scratch namespace for experimentation. |
aingle_sandbox_delete | Delete a sandbox, removing every triple under it. |
Two of those genuinely destroy data: aingle_delete_triple removes a fact outright, and aingle_dag_prune drops history. The "nothing is ever deleted" principle describes how ordinary editing works — a superseded note is retracted with a signed action rather than erased — but it is not an absolute property of the system, and these tools are the exception. They are one more reason to leave a connected client read-only unless you have a specific reason not to.
Related
Reference overview
The section this page belongs to.
Connect your AI
One-click setup for Claude Desktop, Claude Code, Cursor, VS Code and Windsurf.
Grounded, cited answers
What aingle_ground powers.
What your AI sees
The transparency view over exactly this context.
Semantic graph
The triple store the graph-query tools run against.
Glossary
Definitions for MCP, provenance anchor, groundedness, and more.
If you've ingested a codebase, a second endpoint at http://127.0.0.1:19191/mcp-code exposes the code-cartography tools — impact analysis, symbol lookup, code Q&A, code history, the project map, and drift checking. Point your client at it as well if you want code questions answered.