vault_graph_search
Cross-domain / multi-hop semantic search with wikilink graph expansion (GraphRAG). Seeds by vector similarity, expands through the links_to graph (vault_edges), and fuses by RRF. Run index_vault first so the edge graph is populated. Returns chunks tagged seed|expansion with hop + via_edge. Optional vaults[] federates the same query across additional vaults (max 8), fusing per-vault ranked lists by RRF; each result is tagged with its source vault. response_format=concise returns {chunk_id, path, content, rerank_score} per result (plus vault and changed_since_d when set) without source, hop, via_edge and root_seed, and drops route, query, hyde, variants_used, coverage, vaults_used and per_vault; mode_used, failed_variants and failed_vaults are kept.
| Domain | knowledge |
| Scopes | read:notes |
| Access | read |
| Tags | read-only, domain:knowledge, knowledge, search, external-network |
| Profile | core, full |
Annotations
Section titled “Annotations”| Annotation | Value |
|---|---|
| Read-only | yes |
| Destructive | no |
| Idempotent | no |
| Accepts an idempotency key | no |
Idempotent is the advisory MCP idempotentHint. Destructive is also yes for a tool that
asks for confirmation only on some calls.
Confirmation (human in the loop)
Section titled “Confirmation (human in the loop)”No human confirmation is required to call this tool.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
vault |
string |
— | Vault id. May be omitted when only one vault is available. length 1–64; pattern ^[a-z0-9_-]+$ |
|
query |
string |
yes | — | length ≥ 1 |
hypothetical_answer |
string |
— | length ≤ 4000 | |
queries |
string[] |
— | items ≤ 8 | |
vaults |
string[] |
— | items ≤ 8 | |
final_top_k |
integer |
10 |
range 1–100 | |
as_of |
integer |
— | range ≥ 0 | |
since |
integer |
— | range ≥ 0 | |
response_format |
enum |
— | concise returns only the high-signal fields; detailed (the shipped default) returns the full payload. Errors and safety warnings are never trimmed. When omitted, the server’s tools.defaults.responseFormat applies. One of: "concise", "detailed" |
|
verbosity |
enum |
— | Legacy alias for response_format: terse = concise, full = detailed. One of: "full", "terse" |
Output
Section titled “Output”| Field | Type | Always present | Description |
|---|---|---|---|
vault |
string |
yes | — |
mode_used |
enum |
yes | One of: "lexical-route", "graph" |
route |
string[] |
— | |
query |
string |
— | |
hyde |
boolean |
— | |
variants_used |
number |
— | |
failed_variants |
number |
— | |
coverage |
object |
— | |
coverage.arms |
enum[] |
with parent | — |
coverage.armsContributed |
number |
with parent | — |
coverage.armsPossible |
number |
with parent | — |
coverage.expansionSkipped |
boolean |
with parent | — |
coverage.expansionTruncated |
boolean |
with parent | — |
coverage.requested |
number |
with parent | — |
coverage.returned |
number |
with parent | — |
coverage.underfilled |
boolean |
with parent | — |
coverage.staleReturned |
number |
with parent | — |
coverage.staleUnknown |
number |
with parent | — |
coverage.staleThresholdDays |
number |
with parent | — |
coverage.confidence |
object |
with parent | — |
vaults_used |
number |
— | |
failed_vaults |
number |
— | |
per_vault |
Record<string, object> |
— | |
results |
object[] |
yes | — |
results[].chunk_id |
string |
yes | — |
results[].path |
string |
yes | — |
results[].content |
string |
— | |
results[].source |
enum |
One of: "seed", "expansion", "lexical", "sparse", "temporal", "summary", "cluster_summary" |
|
results[].hop |
number |
— | |
results[].via_edge |
object | null |
— |
4 more field(s) not shown; describe_capability returns the full output schema.
Related tools
Section titled “Related tools”Other tools in the knowledge domain: add_observation, audit_provenance, close_goal, commit_capture, commit_wiki_page, create_entity, delete_entity, diagnose_retrieval, draft_wiki_page, end_session, enqueue_capture, episode_stats, explain_answer, find_existing_page, gap_report, get_entity, get_session_traces, knowledge_challenge, link_entities, lint_wiki, list_capture_queue, list_contradictions, list_goals, note_quality_report, plur_get, plur_recall, plur_recall_hybrid, plur_similarity_search, query_entity_graph, record_retrieval_feedback, reflect, rename_entity, session_bootstrap, set_goal, start_session, unlink_entities, update_observation, vault_context, work_episode_chain, work_episodes, work_forget, work_result, work_search.
Back to the tool catalog.