Proto-OKN Unified Knowledge Graph Server
Registry code: f72bb403b2c5ccde
You have access to 27 Proto-OKN knowledge graphs through a single unified server.
WORKFLOW FOR CROSS-GRAPH ANALYSIS:
- endpoint
- https://apps.okn.us/okn-mcp/mcp
- protocol
- http-sse ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is Proto-OKN Unified Knowledge Graph Server live?
- Yes — it answered the hub's last check (checked 12h ago). It answered 100% of checks over the last 30 days.
- Is Proto-OKN Unified Knowledge Graph Server free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does Proto-OKN Unified Knowledge Graph Server have?
- 13 tools: multi_graph_query, route_query, get_schema, get_description, query, get_join_strategy, lookup_uri, get_descendants, ….
- Is Proto-OKN Unified Knowledge Graph Server safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 100%· all time 100%
last good check
of 13 tools
- unknown → live
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
list_graphs open 12h ago
List all available Proto-OKN knowledge graphs with their metadata. Call this first to understand what data is available. Returns graph names, descriptions, domain tags, entity types, and identifier namespaces. Args: domain: Optional filter by domain tag (e.g., "biology", "health", "toxicology", "environment", "geospatial") entity_type: Optional filter by entity class name (e.g., "Gene", "Disease", "ChemicalEntity") Returns: Dictionary with graph_count and graphs list.
{ "type": "object", "title": "list_graphsArguments", "properties": { "domain": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Domain", "default": null }, "entity_type": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Entity Type", "default": null } } }arguments 30 linesmulti_graph_query unknown never probed
Execute different SPARQL queries against multiple knowledge graphs in one call. Each graph gets its own tailored SPARQL query designed for that graph's specific schema. Results are returned with a source_graph column prepended. WORKFLOW: 1. Call get_schema() for each graph first to understand its schema 2. Write graph-specific SPARQL for each graph 3. Submit all queries here in one call 4. Use get_join_strategy() to understand how to merge results on shared identifiers Args: queries: Dictionary mapping graph names to SPARQL query strings. Example: {"spoke-okn": "SELECT ...", "biobricks-ice": "SELECT ..."} Returns: Dictionary with combined results, per-graph counts, and any errors.
{ "type": "object", "title": "multi_graph_queryArguments", "required": [ "queries" ], "properties": { "queries": { "type": "object", "title": "Queries", "additionalProperties": { "type": "string" } } } }arguments 16 linesroute_query unknown never probed
Rank knowledge graphs by lexical overlap with a question. This is a keyword (bag-of-words) prefilter, NOT a learned or semantic router. The question is lowercased and split on whitespace; each term is substring-matched against registry metadata (description summary, domain tags, entity classes, predicates, example queries, identifier namespaces, graph name), with per-field weights summed into `relevance_score`. There is no embedding model, no synonym or stemming expansion, and no training. A question phrased with vocabulary absent from the registry (e.g. "cancer" where the registry says "neoplasm") will score zero. Because of that, ALL graphs are returned ranked rather than filtered to a top-k: the score is a hint to order inspection, and the calling model is expected to make the actual graph selection from the returned metadata (and from get_description / get_schema). Args: question: Natural language question (e.g., "What drugs treat diabetes?", "Where are PFAS contamination sites?") Returns: Dictionary with question, candidate_count, and candidates list sorted by relevance_score (highest first). A score of 0 means no keyword overlap, not "irrelevant".
{ "type": "object", "title": "route_queryArguments", "required": [ "question" ], "properties": { "question": { "type": "string", "title": "Question" } } }arguments 13 linesget_schema unknown never probed
Get the schema (classes, predicates, edge properties) for a knowledge graph. MUST be called before writing SPARQL queries for a graph to understand its specific entity types, predicates, and property names. Args: graph_name: Name of the graph (e.g., "spoke-okn", "biobricks-tox21") compact: If True, return compact format (default) Returns: Schema dictionary with classes, predicates, edge_properties, node_properties.
{ "type": "object", "title": "get_schemaArguments", "required": [ "graph_name" ], "properties": { "compact": { "type": "boolean", "title": "Compact", "default": true }, "graph_name": { "type": "string", "title": "Graph Name" } } }arguments 18 linesget_description unknown 38h ago
Get the full description and metadata for a knowledge graph. Returns the graph's registry content plus additional metadata including domain tags, identifier namespaces, and example queries. Args: graph_name: Name of the graph (e.g., "spoke-okn") Returns: Dictionary with description, domain_tags, identifier_namespaces, etc.
{ "type": "object", "title": "get_descriptionArguments", "required": [ "graph_name" ], "properties": { "graph_name": { "type": "string", "title": "Graph Name" } } }arguments 13 linesquery unknown never probed
Execute a SPARQL query against a specific knowledge graph. Supports automatic ontology expansion (MONDO, UBERON, etc.), query analysis with warnings, and FROM clause injection. The FROM clause is automatically added to scope the query to the correct named graph. IMPORTANT: Call get_schema() first to understand the graph's entity types and predicates before writing your SPARQL query. Args: graph_name: Name of the graph to query (e.g., "spoke-okn") query_string: SPARQL query string analyze: If True, analyze query for potential issues (default: True) auto_expand_descendants: If True, automatically expand ontology URIs to include descendants (default: True) max_descendants: Maximum descendants per URI expansion (default: 2000) bind_expansion_to: Optional list of variable names to bind expanded URIs to Returns: Dictionary with columns, data, count, and optional analysis/expansion info.
{ "type": "object", "title": "queryArguments", "required": [ "graph_name", "query_string" ], "properties": { "analyze": { "type": "boolean", "title": "Analyze", "default": true }, "graph_name": { "type": "string", "title": "Graph Name" }, "query_string": { "type": "string", "title": "Query String" }, "max_descendants": { "type": "integer", "title": "Max Descendants", "default": 2000 }, "bind_expansion_to": { "anyOf": [ { "type": "array", "items": { "type": "string" } }, { "type": "null" } ], "title": "Bind Expansion To", "default": null }, "auto_expand_descendants": { "type": "boolean", "title": "Auto Expand Descendants", "default": true } } }arguments 48 linesget_join_strategy unknown 12h ago
Get the recommended strategy for joining results from two knowledge graphs. Returns shared identifier namespaces and a description of how to merge results. Especially important for gene identifiers, which vary across graphs (Ensembl in spoke-okn, NCBI Gene in spoke-genelab, both in gene-expression-atlas-okn). Args: graph_a: First graph name graph_b: Second graph name Returns: Dictionary with can_join, common_identifiers, strategy description, and optionally bridge graph info for gene identifier conversion.
{ "type": "object", "title": "get_join_strategyArguments", "required": [ "graph_a", "graph_b" ], "properties": { "graph_a": { "type": "string", "title": "Graph A" }, "graph_b": { "type": "string", "title": "Graph B" } } }arguments 18 lineslookup_uri unknown never probed
Look up the URI for an ontology term by its label (name) in Ubergraph. Graph-independent ontology lookup. Use when you have a human-readable term like "muscle organ" or "rheumatoid arthritis" and need the corresponding ontology URI for use in SPARQL queries. Args: label: The term to search for (matched across common casings) max_results: Maximum number of matching URIs to return (default: 2000) Returns: Dictionary with query_label, match_count, and matches list.
{ "type": "object", "title": "lookup_uriArguments", "required": [ "label" ], "properties": { "label": { "type": "string", "title": "Label" }, "max_results": { "type": "integer", "title": "Max Results", "default": 2000 } } }arguments 18 linesget_descendants unknown 38h ago
Expand a URI to find all its descendant classes in the ontology hierarchy. Graph-independent ontology hierarchy expansion via Ubergraph. Use to explore ontology structure (e.g., "what types of arthritis exist?"). For querying datasets with ontology expansion, use the query() tool with auto_expand_descendants=True instead. Args: uri: The full URI to expand (e.g., 'http://purl.obolibrary.org/obo/MONDO_0005178') max_results: Maximum number of descendants to return (default: 2000). Truncation is reported in `truncated` / `total_count`. include_distance: If True, include hierarchy distance from root URI Returns: Dictionary with uri, label, descendant_count, total_count, truncated, descendants. `truncated` is True when max_results cut the list.
{ "type": "object", "title": "get_descendantsArguments", "required": [ "uri" ], "properties": { "uri": { "type": "string", "title": "Uri" }, "max_results": { "type": "integer", "title": "Max Results", "default": 2000 }, "include_distance": { "type": "boolean", "title": "Include Distance", "default": true } } }arguments 23 linesget_query_template unknown 12h ago
Get a query template for a specific relationship, especially useful for edges with properties. This tool retrieves the appropriate query template based on the schema, showing the RDF reification pattern for querying relationships that have edge properties (like MEASURED_DIFFERENTIAL_EXPRESSION, MEASURED_DIFFERENTIAL_METHYLATION, etc.). Args: graph_name: Name of the graph (e.g., "spoke-genelab") relationship_name: Name of the relationship (e.g., 'MEASURED_DIFFERENTIAL_EXPRESSION_ASmMG') Returns: A ready-to-use SPARQL query template showing the RDF reification pattern for this relationship.
{ "type": "object", "title": "get_query_templateArguments", "required": [ "graph_name", "relationship_name" ], "properties": { "graph_name": { "type": "string", "title": "Graph Name" }, "relationship_name": { "type": "string", "title": "Relationship Name" } } }arguments 18 linesclean_mermaid_diagram unknown never probed
Clean a Mermaid class diagram by removing unwanted elements. This tool removes: - All note statements that would render as unreadable yellow boxes - Empty curly braces from class definitions (handles both single-line and multi-line) - Strings after newline characters (e.g., truncates "ClassName\nextra" to "ClassName") - Vertical bars | (invalid in class diagrams) Args: mermaid_content: The raw Mermaid class diagram content Returns: Cleaned Mermaid content with note statements, empty braces, and post-newline strings removed.
{ "type": "object", "title": "clean_mermaid_diagramArguments", "required": [ "mermaid_content" ], "properties": { "mermaid_content": { "type": "string", "title": "Mermaid Content" } } }arguments 13 linescreate_chat_transcript unknown never probed
Generate a prompt template for creating a markdown chat transcript. Returns formatting guidelines and a template for documenting knowledge graph analysis sessions as reproducible markdown transcripts. Args: graph_name: Optional graph name for the filename. If not provided, uses "proto-okn" as a default prefix. Returns: A string containing the transcript template with formatting instructions.
{ "type": "object", "title": "create_chat_transcriptArguments", "properties": { "graph_name": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Graph Name", "default": null } } }arguments 18 linesvisualize_schema unknown never probed
Generate a comprehensive prompt for creating a Mermaid class diagram of a knowledge graph schema. Returns step-by-step instructions for generating, cleaning, and saving a publication-quality schema diagram. Includes handling of edges with properties as intermediary classes. Args: graph_name: Name of the graph to visualize (e.g., "spoke-genelab") Returns: A string containing the step-by-step visualization workflow.
{ "type": "object", "title": "visualize_schemaArguments", "required": [ "graph_name" ], "properties": { "graph_name": { "type": "string", "title": "Graph Name" } } }arguments 13 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's idf72bb403b2c5ccde.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/f72bb403b2c5ccde/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/f72bb403b2c5ccde?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.