About Overdrive Intel
AI coding ecosystem intelligence: breaking changes, tools, security alerts from 900+ sources
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y intel-overdrive-mcpOVERDRIVE_API_KEYSecretAPI key for authenticationOVERDRIVE_API_URLAPI base URLLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
1Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| days | number | No | How many days back to look (for "feed", "breaking", and "briefing" types). Default: 7 |
| type | enum | No | What kind of answer you need: - "search" — find tools, best practices, docs (DEFAULT for most questions) - "similar" — semantic comparison: "X vs Y", "alternatives to X" (uses vector similarity) - "feed" — recent updates, releases, changelogs ("what's new", "latest") - "breaking" — breaking changes, deprecations, urgent issues - "action-items" — security alerts and items needing immediate attention - "briefing" — summarized intelligence pack on a topic - "library" — topic summaries with key points and gotchas (for full docs, use Context7 instead) - "status" — pipeline health checksearch | feed | breaking | briefing | library | similar | action-items | status |
| query | string | Yes | Short keyword query (2-5 words). Extract the core topic from the user's question. Examples: "MCP browser automation", "Claude Code hooks gotchas", "LangChain vs CrewAI", "OpenAI SDK breaking changes", "embedding models code search" |
| feed_tag | string | No | Filter feed by tag (for "feed" type only). Examples: "anthropic", "mcp", "claude-code" |
| feedback | array | No | Report on items from previous calls (fire-and-forget, never delays results) |
| feed_type | string | No | Filter feed by content type (for "feed" type only). Examples: "github_release", "rss_item" |
| telemetry | boolean | No | Set to false to disable feedback/context_stack write-back (default: true) |
| feed_persona | string | No | Filter feed by persona/audience (for "feed" type only). Examples: "developer", "researcher" |
| context_stack | array | No | AI-related packages from the current project (e.g. ["anthropic", "langchain"]). Personalizes results. |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.