ToremLabs/heuresis-mcp

(Legacy snapshot mode) Counts of nodes/edges/projects/ideas + a one-line overview of each project and idea. Always start here when you don't know what's in the workspace.

(Legacy snapshot mode) Every project in the snapshot with brief, direction, lifecycle, and member count.

(Legacy snapshot mode) Substring search across concept labels, descriptions, tags, and partition attributes.

(Legacy snapshot mode) One concept by id, optionally with ancestry, children, and idea memberships.

(Legacy snapshot mode) A node and its descendants up to a given depth.

(Legacy snapshot mode) Every node + edge inside one project. Returns a graph the agent can reason over end-to-end.

(Legacy snapshot mode) Nodes the user has explicitly resolved (validated, starred, or archived) recently.

List concepts in the workspace or one project. Returns id / label / status / parentId / tags up to `limit` entries (default 500). Use BEFORE making changes to learn what already exists.

List every edge in the workspace (or restricted to a project). Filter by kind: partition / k-ref / semantic-adjacency / derived-from / imported-from.

Find concepts by label/substring match. Returns up to k hits, each with id, label, status.

Create a new concept (Node). If parentId is given, the concept becomes a CHILD of that concept and a partition edge is auto-created. If parentId is omitted, the concept attaches to the project root.

Update an existing concept's label, description, tags, partitionAttribute, rationale, or status. Only the fields provided are changed.

Create an edge between two concepts. kind is one of: 'k-ref' (knowledge reference), 'derived-from' (provenance link), 'semantic-adjacency' (sibling kinship). Partition (parent/child) edges are managed via add_concept / set_parent.

Convenience: create a k-ref (knowledge reference) edge from fromId → toId. Equivalent to link_concepts with kind=k-ref.

Mark a concept as validated (status=validated). Optionally also overwrite `rationale`. Idempotent on already-validated nodes.

Set a concept's STANDING — how known / proven the idea is in the wider world. `standing` ∈ 'novel' | 'emerging' | 'established' | 'unknown'. `rationale` is a one-sentence justification (saved as `standing_rationale`). Use this when classifying / judging novelty.

Archive a concept (status=archived). Reversible via unarchive_concept.

Revive a previously-archived concept (status=open). Idempotent on already-open nodes.

Toggle the starred flag on a concept (user-favorite marker).

Hard-delete a concept and its descendants (walks the subtree via parent_id AND partition edges). Edges and project/idea memberships cascade via FK. Refuses to delete a project root node. For many at once, use remove_concepts.

Bulk hard-delete: delete many concepts in one call (each cascades its own subtree). Returns per-id results. Ids already swept up in another id's cascade come back ok:false (not-found) — expected, not fatal. Pair with find_orphans for cleanup.

Surface concepts no normal traversal reaches, scoped to your workspace: 'projectless' (in no project — typically left behind by delete_project) and 'danglingParent' (parent_id points at a deleted node). Read-only. Clean up with remove_concepts (delete) or set_parent (re-home).

Create many concepts in a single atomic transaction. `items` is an array; each item carries label / description? / parentId? / projectId? / tags?. project_id is resolved per-item (explicit > inherited from parent > workspace solo project). Returns the created ids in input order.

Re-parent an existing concept: nodeId's parent becomes newParentId (or detached when null). Updates BOTH node.parent_id AND the partition edge so the canvas tree stays in sync.

Create a new Idea (a named grouping of concepts) with an optional color and optional starting node membership.

Rename an Idea.

Change an Idea's color (any CSS color string).

Replace an Idea's full membership with `nodeIds`. Reconciles the junction table: inserts missing pairs, deletes pairs no longer in the set. Returns added / removed counts.

Add a single concept to an existing Idea (idempotent).

Delete an Idea. Membership rows cascade via FK; the underlying concepts are untouched.

Create a new Project (problem-with-direction) with a name and brief. Optional `direction`.

Update a project's name / brief / direction / lifecycle. Only fields provided are changed.

Delete a project. By default its concepts are LEFT behind as orphans (find them later with find_orphans). Pass deleteNodes:true to also hard-delete every concept in the project (each cascades its subtree) so no orphans are created.

Run an ASIT / TRIZ / Contradiction / Free / Combine / Explore operator against one concept (the anchor). Returns CANDIDATE concepts WITHOUT committing them — call `bulk_add_concepts` (or `run_operator_and_commit`) to persist. Use this when you want the agent to vet the candidates before writing. The…

Same as `run_operator`, but immediately writes every top-level candidate as a child of the anchor with a partition edge and a provenance row stamped origin='mcp'. Use when the agent is confident the candidates should land directly on the canvas (e.g. inside an autonomous expand loop). Children-of-ch…

Recursive Branch — expand a concept by `breadth` children at each of `depth` levels (depth*breadth ≤ 60). Commits each level immediately so the webapp shows partial results as the run progresses. Optionally takes an `angle` hint that biases the underlying EXPLORE operator. Best when the anchor has f…

Fetch an async operator run by its runId. Returns { status: "running" | "done" | "error" }; when "done", the `result` field holds the operator output (candidates / committedIds). Waits up to ~8s for completion before returning, so a simple poll loop converges fast. run_operator / run_operator_and_co…