Skillget

quickcontext

mcp
Security Audit
Warn
Health Warn
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This tool is a local code context engine designed to provide intelligent code indexing, retrieval, and search capabilities. It uses a Rust backend for parsing and a Python SDK to integrate these features via a FastMCP server.

Security Assessment
The overall risk is rated as Low. The automated code scan checked 12 files and found no dangerous patterns, hardcoded secrets, or requests for excessive system permissions. The tool is designed to run locally and relies on a configuration file (`quickcontext.json`) for its settings, which can easily be reviewed by the user. While the setup process does run local bootstrap scripts and the engine natively supports orchestration for external services like Qdrant via Docker, this is expected behavior for a local indexing utility. Network requests are primarily limited to interacting with your configured vector database or optional cloud embedding APIs, keeping external data exposure strictly user-controlled.

Quality Assessment
The project has very recent active development, with the last push occurring today. It is fully licensed under the permissive Apache-2.0. However, the repository suffers from extremely low community visibility, currently sitting at only 5 GitHub stars. The documentation is highly detailed and well-structured, offering clear instructions for setup, validation, and configuration across multiple operating systems.

Verdict
Safe to use, though you should expect a solo-project level of support given the low community adoption.
SUMMARY

Local code context engine with a Rust parsing/search service and a Python indexing/retrieval engine.

README.md

quickcontext

quickcontext

quickcontext is a local code context engine built around a long-lived Rust service and a Python SDK.

The repository has four main surfaces:

  • engine/
    Python SDK for indexing, retrieval, embeddings, Qdrant orchestration, and wrapper-friendly APIs
  • CLI
    Terminal surface for setup, indexing, maintenance, inspection, and benchmarking
  • qc_mcp/
    Thin FastMCP wrapper over the SDK
  • service/
    Rust backend for parsing, grep, symbol lookup, text search, import graphs, protocol extraction, pattern matching, file operations, and IPC

Quick Start

Use the bootstrap flow for the fastest local setup.

Windows:

.\scripts\setup_quickcontext.ps1

Cross-platform:

python scripts/bootstrap_quickcontext.py

If quickcontext.json already exists, the bootstrap keeps the existing provider and API settings and only fills in missing runtime defaults.

After bootstrap:

.venv/Scripts/python.exe -m engine status
.venv/Scripts/python.exe -m engine index . --project quickcontext --no-descriptions
.venv/Scripts/python.exe -m qc_mcp

Documentation

Detailed docs are split by surface:

Agent-facing implementation notes live in AI_DOCS.md.

Configuration

quickcontext reads quickcontext.json or .quickcontext.json.

Start from one of these examples:

  • quickcontext.local.example.json
    Local Qdrant, local embeddings, no API keys required
  • quickcontext.example.json
    Cloud embeddings and LLM configuration

The JSON config model includes:

  • qdrant
  • code_embedding
  • desc_embedding
  • llm
  • service
  • transport
  • mcp

Validation

Useful validation commands:

cargo check --manifest-path service/Cargo.toml
cargo test --manifest-path service/Cargo.toml
python -m py_compile engine/src/pipe.py engine/src/parsing.py engine/src/cli.py engine/__init__.py
venv/Scripts/python.exe -m unittest engine.tests.test_regressions engine.tests.test_mcp_server engine.tests.test_bootstrap_setup

Requirements

  • Python 3.10 or newer
  • Rust toolchain with Cargo
  • Native build tooling for the tree-sitter grammar crates
  • Docker if you want local Qdrant with docker compose
  • Windows or Linux

License

This project is licensed under Apache-2.0. See LICENSE.

Reviews (0)

No results found