MCP Tools

Graphomics exposes its capabilities as Model Context Protocol tools over streamable HTTP. Connect an MCP-capable client to your Graphomics MCP endpoint (see the Quickstart) and call the tools below directly from your agent.

Knowledge-graph tools

Tool	Purpose
`query_graph`	Run a read-only query against the knowledge graph and return rows.
`list_databases`	List the databases in the federated graph and their status.
`get_schema`	Return the node labels and relationship types for a database.
`provenance_record_finding`	Write an Experiment → Analysis → Assertion chain and project graph edges.
`provenance_lineage`	Trace experiment → analysis → assertion lineage for an entity (optionally as-of a timestamp).

MapForge tools

Build and extend the knowledge graph. See the MapForge guide for the end-to-end workflow.

Tool	Purpose
`mapforge_create_bundle`	Create an empty bundle/session; returns a `bundle_dir`.
`mapforge_inspect`	Profile a source file: columns, inferred types, row-count estimate, samples.
`mapforge_templates_list`	List built-in discipline templates (`{name, version, description}`).
`mapforge_templates_show`	Return the full YAML of one named template.
`mapforge_map_heuristic`	Draft a `mapping.yaml` from the column profile (optional `schema_config`).
`mapforge_resolve`	Resolve source entities against the graph; write `resolution.json`.
`mapforge_plan`	Plan ingest routing; write `routing.yaml`.
`mapforge_emit`	Generate Cypher from the resolved bundle.
`mapforge_approve`	Human approval gate; record reviewer and timestamp.
`mapforge_submit`	Execute the approved Cypher against the graph (gated on approval).

Workbench tools

Run validated pipelines, publish custom nodes, and manage files. See the Workbench guide.

Catalog & authoring

Tool	Purpose
`list_nodes`	Compact node catalog (id, name, category, inputs, outputs, parameters).
`get_node`	Full details for a single node by id.
`list_skills`	List skills (procedural recipes) — built-in + your organization's.
`get_skill`	Get a skill's recipe.
`start_skill_run`	Begin a skill run and bind its referenced tools.
`create_skill`	Author and store a new skill for your organization.
`list_custom_nodes`	List your organization's custom nodes.
`get_custom_node`	Full details for one custom node.
`publish_custom_node`	Publish a Jupyter notebook (`.ipynb`) as a custom node.
`publish_python_node`	Publish raw Python (`def execute(params)`) as a reusable node.
`publish_model_node`	Publish a train/infer model script as a paired train + infer node.

Execution

Tool	Purpose
`validate_workflow_tool`	Validate a workflow definition against the node catalog.
`create_and_execute`	Create and execute a pipeline (the primary run tool).
`get_execution_status`	Poll execution progress: status, percent complete, task states.
`get_execution_results`	Fetch completed-run results with artifact URLs.
`cancel_execution`	Cancel a running execution.
`get_task_output`	Inspect intermediate task outputs.
`get_task_image_url`	Get download URLs for visualization images.

Files & utilities

Tool	Purpose
`upload_file`	Upload a local file to Workbench storage.
`upload_file_content`	Upload a file by base64 content.
`stage_file_content`	Stage inline text content as a file.
`download_file`	Get download URLs for output files.
`list_files`	Browse folders and files in storage.
`search_files`	Search files by name.
`preview_file`	Preview a text file without downloading.
`taxonomy_lookup`	Look up a taxonomic name (NCBI / MetaPhlAn) and crosswalk entries.