Enterprise DNAEnterprise DNA

MCP Servers

SonAIengine/graph-tool-call

Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP / LangChain.

Our verdict

Not reviewed yet

We have not reviewed SonAIengine/graph-tool-call yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About SonAIengine/graph-tool-call

A Python library for graph-based tool retrieval in LLM agents. It selects relevant tools from a set of up to 248 tools using a graph structure, achieving 82% accuracy while consuming 79% fewer tokens than baseline approaches. The library has zero external dependencies and supports OpenAPI, MCP, and LangChain integrations.

Best for

Developers building LLM agents that need efficient tool selection from a large tool set

Use cases

  • Selecting tools for LLM agents with minimal token overhead
  • Integrating graph-based tool retrieval into agent workflows via OpenAPI or MCP
  • Reducing context lengths when managing large tool inventories

Notes

7 stars on GitHub. Last updated 2026-05-06. Licensed MIT.

Pros

  • Zero dependencies, lightweight and easy to embed
  • Substantial token savings (79%) without major accuracy tradeoff
  • Supports multiple standard interfaces (OpenAPI, MCP, LangChain)

Cons

  • Limited community adoption (7 GitHub stars)
  • Python-only, not available for other languages
  • 82% accuracy on 248 tools may degrade with much larger tool sets

Key facts

What we have checked

Days since the last commit
22
Checked GitHub
GitHub forks
3
Checked GitHub
GitHub stars
17
Checked GitHub
Open issues
1
Checked GitHub
Releases in the last 90 days
14
Checked GitHub

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

How to use

How to set it up

As the listing publishes it. We have not run this install.

Install

uvx graph-tool-call demo dependency-chain

Tools exposed

  • embedding-local

Clients the listing names (not checked here)

Claude Code, Cursor, Windsurf, ChatGPT

Install

Add SonAIengine/graph-tool-call to your client

Not verified yet

No install recipe yet. We write one for Claude Code, Claude Desktop, Cursor, VS Code, Codex and ChatGPT when the server is in the official MCP registry with a package or remote address we can use.

Until then, follow the project's own README, or the setup the listing publishes under How to set it up.

Works with

What SonAIengine/graph-tool-call connects to

No confirmed connections yet. A product appears here when the server's registry name, repo, homepage or name ties it to that product, and a client appears when we have an install recipe for it.

Health and security

Is SonAIengine/graph-tool-call looked after, and what do its setup files show

Health score

56 out of 100

Does someone look after this repository? It does not say the code is good or safe. Worked out from GitHub signals checked . How it is worked out

PartPointsWhat we saw
Recent activity30 of 30Last push 22 days ago
Releases15 of 1514 releases in 90 days
Issue repliesNot countedThe latest check has no issue response reading (fewer than 3 measured issues, or issues switched off)
Maintainer0 of 15Owned by a single user
Official source0 of 20Community server

Security check static checks

100 out of 100

Reads what is published about the server: package advisories, licence, secrets in the documented setup and tool permissions. Nothing is installed or run, so this is not a security assessment. Checked by edna-static-v1 PyPI:graph-tool-call@0.47.0. What it checks

Licence: MIT

  • Note The lab has not recorded this server's tool list yet, so tool permissions were not checked.

Sources

Where this comes from

  • GitHubRegistry

    Checked · Days since the last commit, GitHub forks, GitHub stars, Open issues, Releases in the last 90 days

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.