PasNavigator MCP
Enables semantic navigation and symbol lookup in Delphi/Pascal codebases, providing ranked symbol search, hierarchy exploration, and source retrieval.
README
PasNavigator MCP
MCP server for semantic navigation in Delphi/Pascal codebases.
The long-term design is:
- Delphi-based indexer/backend that reuses ideas and code from
CodeComparer - thin MCP server layer that exposes project indexing and symbol navigation tools
- compact symbol-level responses for AI agents instead of raw grep output
Current status
This repository contains:
- Python MCP tool surface and process adapter
- Delphi console backend with vendored CodeComparer/DelphiAST sources under
delphi/vendor/codecomparer/ - no runtime dependency on a live CodeComparer repository checkout
DevExpress VCL is still required to compile the Delphi indexer (DXVCL).
The vendored importer carries a few local changes so that defines and
unit_scopes reach the parser; they are listed in
delphi/vendor/codecomparer/NOTICE.txt.
Docs:
- protocol:
docs/delphi-backend-protocol.md - Delphi build:
delphi/README.md
Tools
open_project,open_project_from_configproject_statusfind_symbol— ranked, capped, reportstotal_countget_symbolget_hierarchyget_descendantsget_source
Configuration
Example project configuration:
{
"project_name": "MyApp",
"roots": [
"E:/Work/MyApp/Source",
"E:/Work/MyApp/Modules"
],
"search_paths": [
"E:/Libs/Common",
"C:/RAD/Studio/22.0/source/vcl"
],
"defines": ["MSWINDOWS", "VER350"],
"unit_scopes": ["System", "Vcl", "Winapi"],
"excludes": ["**/__history/**", "**/backup/**"]
}
Development
Create a virtual environment and install the package in editable mode:
python -m venv .venv
.venv\Scripts\Activate.ps1
pip install -e .
Run the server with the in-memory stub:
python -m pasnavigator_mcp
Talk to the Delphi console backend (stub build, no DevExpress):
$env:PASNAVIGATOR_BACKEND = "delphi"
$env:PASNAVIGATOR_DELPHI_EXE = "E:\Github_dm75\PasNavigator_MCP\delphi\bin\Win32\Debug\PasNavigatorBackend.exe"
python -m pasnavigator_mcp
Run the tests. Cases that need the compiled backend skip themselves when
PasNavigatorBackend.exe is missing; the rest run against a Python fake
process:
python -m unittest discover -s tests
Next step
The MCP layer itself (server.py, config.py) has no test coverage, because
the mcp dependency has not been installable in this environment.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.