Skip to main content
Glama
sqlite-graph-mcp

sqlite-graph-mcp

by developjik

Run a 5-operator plan

graph_plan

Run chained find, walk, filter, and set-difference steps in one call to query a code graph and return nodes, edges, and path:line evidence.

Instructions

Operator 5 (answer): chain find → walk → filter → minus in one call and get structured evidence (nodes, touched edges, path:line citations, per-step trace). Accepts a pipeline string such as find "graph" kind=symbol | walk type=imports depth=2 | filter path=src/** or a JSON {steps:[...]} plan.

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": {
      "plan": "<plan>"
    },
    "name": "graph_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
planYesPipeline string, step array, or {steps:[...]} object.
limitNoMax nodes in the answer (default 50).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does disclose what comes back: nodes, touched edges, path:line citations, and a per-step trace. That is substantive output-shape information beyond the schema. It leaves out the read-only safety profile and failure/partial-failure behavior when a middle step matches nothing.

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?

Two sentences, front-loaded with the action and then the accepted input formats. The leading 'Operator 5 (answer)' label is somewhat cryptic but short; otherwise every clause carries information. Slightly dense syntax nesting in the example, but no wasted prose.

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

Completeness4/5

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

With no output schema and no annotations, the description does the work of explaining what a plan is, what forms it takes, and what evidence comes back. Remaining gaps are the safe/read-only nature of execution, default and maximum node limits, and routing guidance against the single-operator siblings.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents both parameters, establishing a baseline of 3. The description adds real value by giving a concrete pipeline example with operator arguments (kind=symbol, type=imports depth=2, path=src/**), but it does not explain the semantics of the separate top-level limit parameter or how it interacts with a limit embedded in the plan.

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

Purpose4/5

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

States a specific action: chain find → walk → filter → minus into one call and return structured evidence. The framing 'Operator 5 (answer)' is internal jargon, but the concrete operator chain and the accepted inputs (pipeline string or {steps:[...]}) make the tool's role distinguishable from the single-operator siblings like graph_find and graph_walk, even though it does not explicitly name them.

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

Usage Guidelines3/5

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

Usage is only implied: chaining multiple operators at once is implicitly the reason to prefer this over the individual graph_find/graph_walk/graph_filter tools. There is no explicit statement of when to use the pipeline string versus the JSON plan form, nor any guidance on when a single-operator call is preferable.

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