Skip to main content
Glama

Kaleidoscope MCP (SEC & financial data)

Graph Neighbors (typed weighted-signal edges — the traversal primitive) [beta]

graph_neighbors
Read-onlyIdempotent

The traversal primitive — a node's linked entities via typed edges, each with a signals dict carrying that edge's NATURAL weight (no unified edge weight; you pick). Returns edges:[{edge_type, direction, target_node_id, target_type, target_name, signals, as_of, source}]. Second-hop = call again on a returned target_node_id (an insider's OTHER board seats, a fund's co-investors, an institution's alumni). Filters: edge_types (discover valid ones + their signals via graph_schema), order_by a signal DESC, since+as_of (date RANGE — windowed/PIT walks), min_signal+signal_key floor, include_rumored (default false → acquired is definitive-only), limit. Edge set is catalog-driven (mars.graph_edge_catalog) — new edges are usable with no code change; consumer-contract filters (integrity, is_definitive) are baked in per the catalog.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "node_id": "<node_id>"
    },
    "name": "graph_neighbors"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_ofNoUpper date bound (YYYY-MM-DD) — edges dated on/before (PIT).
limitNoMax neighbors per edge type (default 50, max 500).
sinceNoLower date bound (YYYY-MM-DD) — edges dated on/after. Pair with as_of for a window.
node_idYesCanonical node UUID (from graph_resolve).
order_byNoA signal key to sort neighbors by, DESC nulls-last (e.g. 'value_usd', 'deal_value_usd_converted'). Default: pit_column DESC.
node_typeNoOptional — skips the probe.
edge_typesNoRestrict to these edge types (use graph_schema to discover valid ones). Default: all edges this node touches.
min_signalNoNumeric floor on a signal (pair with signal_key).
signal_keyNoWhich signal min_signal applies to.
expand_familyNoDefault true. For family-aware edges (e.g. invested_in), roll the anchor up to its full canonical family before walking (one Invesco member → all members' deals) so graph_neighbors matches mars_investor_portfolio's rollup. Co-investors on one deal collapse to a single edge (no double-count). Set false for a literal single-entity walk.
include_rumoredNoInclude rumored deals on edges with a consumer-contract edge_filter (e.g. acquired). Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds real behavioral context beyond that — catalog-driven edge set, baked-in consumer-contract filters, default expand_family rollup behavior, and rumored-deal exclusion by default. The unusual expand_family default (fanning out to a canonical family) is disclosed but its surprise factor could be flagged more prominently.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core concept and return shape in the first sentence, then filters, then behavioral caveats. Dense but each clause carries information; minor redundancy where the description re-lists filters already documented in the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 11-parameter traversal primitive with no output schema, the description supplies the return shape inline, the second-hop pattern, default behaviors, and the discoverability path via graph_schema. Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds conceptual meaning the schema lacks: there is no unified edge weight and the caller must choose a signal, order_by sorts DESC nulls-last, since+as_of form a window, and min_signal must pair with signal_key. These pairings and the 'you pick' signal philosophy go beyond the field-level descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource — 'a node's linked entities via typed edges' — and immediately names the return shape including every field. It distinguishes itself from siblings by naming graph_schema for edge discovery and graph_resolve for node_id acquisition.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit operational guidance: 'Second-hop = call again on a returned target_node_id' with concrete examples (other board seats, co-investors, alumni), plus a note that expand_family keeps it consistent with mars_investor_portfolio. It never mentions graph_path or graph_aggregate, so the agent must infer when a multi-hop or aggregated traversal is the better alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources