Chroma Package Search

Created By
Chroma9 months ago
Give coding agents the ability to understand dependencies.
Overview

Chroma Package Search is a tool that enhances coding agents by providing them with the ability to understand dependencies in code packages, improving their performance on coding tasks and reducing hallucination risks.

To use Chroma Package Search, create a Chroma account to obtain an API key, and then utilize the provided server command to access the package search functionalities.

  • package_search_grep: Executes a grep over the source code of a public package to find code using regex.
  • package_search_hybrid: Searches package source code using both semantic understanding and regex patterns for hybrid search capabilities.
  • package_search_read_file: Reads specific lines from a source file of a public package, allowing users to fetch code regions by line range.
  1. Enhancing AI coding agents with contextual understanding of code dependencies.
  2. Performing deterministic searches in code packages using regex.
  3. Fetching specific code snippets from public packages for analysis or debugging.
  • How do I get an API key?

Create a Chroma account and get an API key at Chroma Package Search. You will receive $5 worth of free credits for your queries.

  • What is the benefit of using Chroma Package Search?

It improves the performance of coding agents by providing them with ground truth context about code packages, which helps in reducing errors and hallucinations.

Server Config

{
  "mcpServers": {
    "package-search-mcp": {
      "type": "http",
      "url": "https://mcp.trychroma.com/package-search/v1",
      "headers": {
        "x-chroma-token": "<CHROMA_API_TOKEN>"
      }
    }
  }
}
Project Info
Created At
9 months ago
Updated At
9 months ago
Author Name
Chroma
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

3 hours ago