How do I use code-index-pg?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@code-index-pg find all callers of the function validate_token and show their files" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

code-index-pg

by tgt-technology

Overview Schema Source Related Servers Discussions Admin

Python

Local

code-index-pg

Unified code index for Hermes: exact + semantic + call graph search over the TGT One monorepo, persisted in postgres. Replaces the code-index fork, cocoindex and CodeGraphContext with one lightweight MCP server.

Stack

postgres-local (port 5432, DB codeindex) + pgvector 0.8.3
Ollama bge-m3 (1024 dims) for embeddings — no torch in this venv
tree-sitter-language-pack (21 languages) for symbol extraction
fastmcp — single MCP process, no extra daemons

Related MCP server: Tree-Sitter MCP

Install

git clone https://github.com/tgt-technology/code-index-pg.git
cd code-index-pg
uv sync
uv tool install --editable .

DB: la infraestructura (postgres + pgvector, ollama + bge-m3, base codeindex) se levanta con deploy/ — ver Deploy. El esquema de tablas lo aplica el server al arrancar.

Deploy (entorno desde cero)

El índice vive en postgres, no en archivos: reproducir el entorno es levantar la infra, no copiar datos. Todo está en deploy/.

Windows (Docker Desktop + uv):

powershell -NoProfile -File deploy\setup.ps1        # -Gpu si hay GPU NVIDIA

Linux / WSL:

deploy/setup.sh          # --gpu si hay GPU NVIDIA

El script levanta postgres (pgvector) + ollama, crea la base codeindex con la extensión vector, descarga bge-m3, instala el server como uv tool y verifica cada punto al final (falla con mensaje claro si algo quedó a medias).

Después, una sola vez, el índice inicial (~30 min para ~7K archivos):

uv run python -c "from code_index_pg.indexer_pipeline import index_project; print(index_project('/ruta/a/tu/codigo'))"

Registro en Hermes — el wrapper espera a que postgres acepte conexiones antes de lanzar el server (sin eso, el server muere si la BD no está lista):

# Linux / WSL
hermes mcp add codeindex --command /ruta/al/repo/deploy/mcp-wrapper.sh

# Windows
hermes mcp add codeindex --command powershell --args -NoProfile -File C:\ruta\al\repo\deploy\mcp-wrapper.ps1

Solo los servicios van en Docker: el server MCP es stdio y corre en el host, usando los defaults del código (127.0.0.1:5432/codeindex, http://localhost:11434).

Run

# MCP server (stdio — used by the proxy wrapper)
code-index-pg --project-path ~/develop

# Full index (one-time, ~10 min for ~7K files)
python -m code_index_pg.indexer_pipeline  # via test harness, or:
uv run python -c "from code_index_pg.indexer_pipeline import index_project; print(index_project('/home/jam/develop'))"

MCP tools

Tool	Description
`set_project_path`	Index a project and start the incremental watcher
`update_index`	Incremental re-index: add missing files, drop deleted ones (no re-embed)
`search_code`	Literal/regex search over symbol names + file paths (paginated)
`search_semantic`	Embedding similarity search (bge-m3, pgvector cosine)
`callers_of`	Symbols that call the given symbol
`callees_of`	Symbols called by the given symbol
`impact_analysis`	2-level recursive callers + affected files
`find_files`	Glob search over indexed files
`get_symbol_body`	Signature, docstring, location of a symbol
`get_file_summary`	Language, line count, symbols of a file
`get_status`	Indexed projects + counts + active project
`remove_project`	Remove an indexed project and all its data in cascade (rejects the active project)

Hermes integration

Proxy: port 3104 in ~/.hermes/scripts/mcp-proxies.sh (supervisor systemd)
Wrapper: ~/.hermes/scripts/mcp-codeindex-wrapper.sh
Register: hermes mcp add codeindex --url http://127.0.0.1:3104/mcp

Environment

Var	Default	Notes
`CODEINDEX_DATABASE_URL`	`postgres://postgres:postgres@127.0.0.1:5432/codeindex`	local tool
`OLLAMA_URL`	`http://localhost:11434`	embeddings
`CODEINDEX_EMBED_MODEL`	`bge-m3`	must match pgvector dims (1024)
`CODEINDEX_PROJECT`	unset	active project (set via `set_project_path`)

Tests

uv run pytest tests/ -q   # unit + contract (in-memory MCP client)

Spec / OpenSpec

Living spec: openspec/specs/code-index/spec.md — archived changes in openspec/changes/archive/ (unified-code-index, project-directory-management).

License

MIT — free to use, modify and redistribute. See LICENSE.

Available Tools

12 tools

callees_ofA

List symbols called by the given symbol.

Inputs: symbol (required). Returns: object

callers_ofB

List symbols that call the given symbol.

Inputs: symbol (required). Returns: object

find_filesC

Find files by glob pattern.

Inputs: glob (required). Returns: object

get_file_summaryB

Summarize a file: language, line count, symbols.

Inputs: path (required). Returns: object

get_statusA

Show indexed projects and counts.

Inputs: no named parameters. Returns: object

get_symbol_bodyA

Get the signature, docstring and location of a symbol.

Inputs: symbol (required). Returns: object

impact_analysisB

2-level recursive callers and affected files for a symbol.

Inputs: symbol (required). Returns: object

remove_projectA

Remove an indexed project and all its data (cascade).

Inputs: path (required). Returns: object

search_codeB

Search symbols and files by literal, regex, or fuzzy match.

Inputs: pattern (required), page, fuzzy, regex, +1 more. Returns: object

search_semanticA

Search code by meaning using embeddings (bge-m3 via Ollama).

Inputs: query (required), limit. Returns: object

set_project_pathC

Index a project directory and make it the active project.

Inputs: path (required). Returns: object

update_indexA

Incremental update: index missing files, drop deleted ones (no re-embed).

Inputs: no named parameters. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

TDQS

A3.6/5.0

Scored 2026-09-10 23:46 across 12 tools

Disambiguation5/5

Each tool targets a distinct operation: indexing, searching (literal vs semantic), graph queries (callers/callees), file operations, and project management. No two tools appear to overlap in purpose.

Naming Consistency4/5

Most tool names follow a clear verb_noun pattern (set_project_path, search_code, get_status). Minor exception: 'callers_of' and 'callees_of' use a different prepositional style, but still readable and predictable.

Tool Count5/5

12 tools is well within the ideal range for a code indexing/search server. Each tool serves a distinct function needed for code navigation and project management, with no redundancy.

Completeness5/5

The surface covers the full lifecycle: project setup, incremental updates, multiple search modes, symbol graph queries, file and symbol detail, and project removal. Missing features like batch re-index or cross-project search are minor and not essential.

Resources

Related MCP Connectors

gently
is.gently
Ask a codebase what calls what: search, blast radius, paths between symbols, and diffs.
Code Analysis Developer Tools
1
https://api.stage.gently.is/mcp
Maguyva
ai.maguyva
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Code Analysis Coding Agents
23
https://maguyva.tools/mcp
Graphify
io.github.Graphify-Labs
Search indexed code, trace dependencies, assess change impact, and recall repository memory.
Code Analysis Knowledge & Memory
1
https://api.graphify.com/mcp
Kuuhaku
dev.kuuhaku
Ask who calls a route, what a change breaks or who reads a field, across a system's repos.
Code Analysis Developer Tools
1
https://api.kuuhaku.dev/mcp

Related MCP Servers

Knowledge Graph MCP Server
Code Analysis Developer Tools Knowledge & Memory
DeepakJangra239
A
license
A
quality
D
maintenance
Enables fast code analysis and navigation through hybrid semantic search, graph-based relationship tracking, and structure exploration across multiple programming languages with optimized indexing for large codebases.
Updated a year ago (2025-12-03 06:39 UTC)
8
3
MIT
Tree-Sitter MCP
Code Analysis Developer Tools Search
nendotools
A
license
Not graded
quality
D
maintenance
Enables fast semantic code search and analysis across 15+ programming languages. Supports searching for functions and classes, tracing code usage, detecting syntax errors, and analyzing code quality and structure.
Updated 8 months ago (2026-03-11 08:49 UTC)
20 npm
33
GPL 3.0
OrgBrain MCP Server
Developer Tools Code Analysis Version Control
irab
A
license
Not graded
quality
D
maintenance
Provides knowledge extraction and cross-repo analysis tools for multi-repository organizations. It enables users to query type definitions, service dependencies, and infrastructure configurations across an entire organization's codebase.
Updated 9 months ago (2026-02-02 20:51 UTC)
MIT
code-intel
Code Analysis Search Knowledge & Memory
nairraf
A
license
Not graded
quality
D
maintenance
Provides semantic code search and code insights via a knowledge graph, enabling AI to understand, navigate, and modify complex projects with deep dependency and architecture analysis.
Updated 8 months ago (2026-03-22 02:55 UTC)
MIT

code-index-pg

Stack

Install

Deploy (entorno desde cero)

Run

MCP tools

Hermes integration

Environment

Tests

Spec / OpenSpec

License

Available Tools

Tool Schema Changelog

TDQS

Resources

Related MCP Connectors

Related MCP Servers

Knowledge Graph MCP Server

Tree-Sitter MCP

OrgBrain MCP Server

code-intel