Skip to main content
Glama
sqlite-graph-mcp

sqlite-graph-mcp

by developjik

Find nodes

graph_find

Search codebase files, symbols, Markdown headings, and packages by text using prefix matching with substring fallback, so partial terms like "index" also find names such as "GraphIndexer".

Instructions

Operator 1 (find): search files, symbols, markdown headings and packages by text. Uses SQLite FTS5 prefix ranking plus substring fallback, so "index" matches "GraphIndexer".

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": {
      "query": "<query>"
    },
    "name": "graph_find"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoRestrict to node kinds.
limitNoDefault 20.
queryYesSearch text, e.g. "walkNodes", "graph", "README". Use "*" to list all.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It does useful work by disclosing the matching engine (FTS5 prefix ranking plus substring fallback) and giving a concrete example ("index" matching "GraphIndexer"), which clarifies recall/ranking behavior that would otherwise be invisible; however, it says nothing about result ordering beyond that, read-only safety, or return shape.

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

Conciseness5/5

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

Two short sentences, no filler, with the core action front-loaded and the matching semantics appended as supporting evidence. Nothing in it could be cut without losing meaning.

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

Completeness3/5

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

With no annotations and no output schema, the description leaves the return value entirely unexplained — an agent does not know whether it gets paths, node kinds, scores, or match snippets. That is acceptable for a simple search tool but is a real gap given nothing else supplies the information.

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 query, kind, and limit including the "*" list-all escape hatch and the default limit of 20. The description adds matching-behavior meaning for query (substring fallback) but nothing for kind or limit, so it sits at the baseline for a well-documented schema.

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?

A specific verb (search) plus a concrete resource set (files, symbols, markdown headings, packages) searched by text. It clearly reads as a text-search tool, though the "Operator 1 (find)" framing hints at a family without naming or contrasting any sibling like graph_filter or graph_walk.

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

Usage Guidelines2/5

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

There is no when-to-use vs when-not-to-use guidance. Given overlapping siblings (graph_filter for narrowing, graph_walk for traversal), an agent gets no signal about when text search is the right entry point or when to switch to a different operator.

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