AgentToolDrop

8 of 66

XERJ

Local search engine and MCP server that indexes code, docs, logs and CSV for agents to query

  • score 63
  • 10.9k stars
  • 96.8 stars/day since creation
  • pushed
  • v1.0.0-rc.97 on
  • Apache-2.0

Install the xerj binary (Linux, macOS)

curl -fsSL https://xerj.org/get | sh

Copied from the project's docs at github.com/xerj-org/xerj

Why you'd want it

XERJ is one Rust binary that indexes code, docs, logs, JSONL/CSV and PDFs and serves BM25, vector and hybrid search behind an Elasticsearch-compatible API. Running xerj autoindex <folder> sniffs each file and creates one index per dataset with no schema to write, and source files go through tree-sitter so code arrives with symbols and line numbers. xerj mcp is an MCP stdio server that proxies to the local node and exposes seventeen tools, including search, hybrid search, memory store and recall, and code search.

Best for

  • Letting an agent search a local codebase by passage
  • Agent memory recalled across sessions
  • Querying logs and JSONL/CSV with Elasticsearch syntax

Use it when

You want a coding agent to query an index of your project, docs or logs through MCP instead of grepping and reading whole files, with the data indexed locally.

Skip it if

The quick start runs the node with --insecure, which the README says turns off TLS and API-key auth so every caller that can reach the port can read and delete every index; it is meant for one user on a dev machine, and a shared host needs the auth-on start with an API key. The installer is a curl | sh script. The optional rerank search stage sends result text to TypeSafe AI's servers once you set a key. The default embedder is lexical, and the neural embedder is opt-in with a download of about 90 MB. The README says passage search for coding is neutral to harmful on popular public libraries the model already knows, and the latest release is a release candidate (v1.0.0-rc.97).

Editor's note

Windows install uses PowerShell: irm https://xerj.org/get.ps1 | iex. After install, xerj mcp needs a running node; the README MCP config block shows the client setup.

Same category or shared tags.

  1. Rank 1

    Parametric 3D CAD in Rust with an MCP server that lets agents model, measure and export parts

    • score 89
    • 7.8k stars
    • 1,414 stars/day last 1 day
    • pushed
    • v0.16.2 on
    • MIT OR Apache-2.0

    Add the MCP server to Claude Code

    claude mcp add solidcraft -- solidcraft-cli mcp
    Use it when, skip it if, stats for SolidCraft

    Why you'd want it

    SolidCraft is an open-source parametric 3D CAD application written in Rust that runs on the desktop and in the browser. Its solidcraft-cli mcp command is an MCP server on stdio with tools such as execute, batch, inspect_design, measure, set_parameter, screenshot and export. Run headless it keeps its own design session, and with --connect it drives the running desktop app so you can watch the agent model. The README shows a rover model, 3,323 timeline steps, that a user built entirely through the MCP server.

    Best for

    • Agent-driven parametric CAD modelling
    • Measuring and screenshotting parts from an agent
    • Scripted CAD runs with STEP or STL export

    Use it when

    You want an agent to build or adjust parametric parts, with dimensions held as parameters, and export them to STEP, STL or 3MF. It also suits watching the agent work live in the desktop app.

    Skip it if

    The README calls it "early but usable for simple parts" and says its reference checks do not establish complete geometric or workflow equivalence, so skip it for complex production CAD. The repo is under two weeks old and has shipped several releases in the last two days. Several MCP tools (execute, save, export, screenshot with a path) can read, write and delete files in the open design's folder and any --allow-path folder, and --allow-any-path lifts that limit. The README also says the downloads are not signed yet.

    Stats

    New and rising score
    89 of 100
    Stars per day, last 1 day
    1,414
    Release
    v0.16.2,
    License
    MIT OR Apache-2.0
    Pricing
    Open source
    Works with
    Claude Code, Any MCP client, macOS, Linux, Windows, Web
    Forks
    899
    Open issues
    1,553
    GitHub checked
  2. Rank 41

    Local-first 3D building editor that AI agents read and change through an MCP server and CLI

    • score 39
    • 25k stars
    • 24.2 stars/day last 5 days
    • pushed
    • @pascal-app/cli@1.0.4 on
    • MIT

    Run the editor with npx

    npx @pascal-app/cli editor
    Use it when, skip it if, stats for Pascal Editor

    Why you'd want it

    Pascal is an open-source, local-first 3D building editor that runs in the browser or from the CLI and connects AI agents through MCP. One npx command starts the editor and an authenticated MCP service on loopback ports and keeps projects in a local SQLite file. The @pascal-app/mcp package exposes scene tools, resources and prompts to MCP-compatible hosts. The repository also ships agent skills and plugins for Claude Code and Codex, including pascal-3d for MCP setup and scene work and furniture-fit for footprint assessments.

    Best for

    • Letting an agent edit a floorplan or building model
    • Furniture footprint checks driven by an agent
    • Self-hosted 3D building projects

    Use it when

    You want an agent to read and modify a 3D building model through MCP, on your own machine or in a self-hosted container.

    Skip it if

    You need agents to work on several clients at once; the README says to use one active agent client per local CLI service. The local CLI needs Node.js 22.13 or newer and downloads the web editor runtime on first start. The Pascal Next demo in the README is a hosted preview and not part of the open-source release. The Claude plugin also bundles a hosted pascal-hosted server that prompts for an optional Pascal API key stored in the OS keychain, and the Docker image is protected by an admin password you set, so review what you connect.

    Stats

    New and rising score
    39 of 100
    Stars per day, last 5 days
    24.2
    Release
    @pascal-app/cli@1.0.4,
    License
    MIT
    Pricing
    Open source
    Works with
    Claude Code, Codex, Any MCP client, Web, Docker
    Forks
    3,111
    Open issues
    62
    GitHub checked
  3. Rank 29

    Connects Claude Code, Codex and other MCP clients to a live Godot editor to build scenes, nodes and scripts

    • score 45
    • 3.1k stars
    • 21 stars/day last 5 days
    • pushed
    • v4.3.0 on
    • MIT
    Use it when, skip it if, stats for Godot AI

    Why you'd want it

    Godot AI is a Godot editor plugin plus a Python MCP server; the README lists 46 tools and 120+ operations to build scenes, edit nodes and scripts, wire signals and configure UI, materials, animation, particles, cameras and environments. GDScript written through the tools is parse-validated, hot-reloaded and attached, while C# support is text-only. A dock inside Godot shows the connection and has a Configure button that writes the client entry for Claude Code, Claude Desktop, Codex, Cursor, VS Code and others.

    Best for

    • Building Godot scenes from prompts
    • GDScript projects in Godot 4.7+
    • Running a game's scene tests from an agent

    Use it when

    You build games in Godot 4.7 or later and want your agent to read and change the open project in the editor instead of editing .tscn files blind.

    Skip it if

    You work mainly in C#, which is text-only (it does not build .NET or report compiler errors), or you are on Godot older than 4.7. Usage telemetry is on unless GODOT_AI_DISABLE_TELEMETRY=true is set, and the agent gets write access to the open project.

    Stats

    New and rising score
    45 of 100
    Stars per day, last 5 days
    21
    Release
    v4.3.0,
    License
    MIT
    Pricing
    Open source
    Works with
    Claude Code, Claude Desktop, Codex, Cursor, VS Code, Any MCP client
    Forks
    179
    Open issues
    37
    GitHub checked

For agents

The same entry, as files an agent can read without scraping this page.

# read one entry
curl -s https://agenttooldrop.com/tools/xerj.md

# list the MCP servers in the catalog
curl -s https://agenttooldrop.com/tools.json \
  | jq -r '.tools[] | select(.category=="mcp-server") | .slug'