driftnet
A local catalogue of the links your chats share: search, save and file them. Any model, or none.
Open the source (opens github.com) https://github.com/kevinchu1110/driftnet
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: AWS_ACCESS_KEY_ID, AWS_BEARER_TOKEN_BEDROCK, AWS_SECRET_ACCESS_KEY, DRIFTNET_LLM_API_KEY. Use a key with the least access you can.
What it is
MCP servers from io.github.KevinChu1110.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
driftnet@1.2.1
From the server's entry in the official MCP Registry
Settings it asks for
DRIFTNET_HOME· Where settings and the catalogue live (default ~/.driftnet)DRIFTNET_LLM_PROVIDER· anthropic, openai, gemini, bedrock, vertex, claude-cli or gemini-cli; empty for no summariesDRIFTNET_LLM_MODEL· Model name for that providerDRIFTNET_LLM_API_KEYsecret · API key for that provider (gemini also reads GEMINI_API_KEY; for vertex it may be a raw access token)DRIFTNET_LLM_BASE_URL· OpenAI-compatible endpoint for the openai provider (Ollama, OpenRouter, Gemini…)DRIFTNET_LLM_REGION· Region for the bedrock provider (or AWS_REGION) and the vertex provider (default us-central1)AWS_ACCESS_KEY_IDsecret · bedrock provider: AWS access key ID (with AWS_SECRET_ACCESS_KEY, and AWS_SESSION_TOKEN for temporary credentials)AWS_SECRET_ACCESS_KEYsecret · bedrock provider: AWS secret access keyAWS_BEARER_TOKEN_BEDROCKsecret · bedrock provider: a Bedrock API key, used instead of the AWS keysGOOGLE_APPLICATION_CREDENTIALS· vertex provider: path to a service-account JSON key file (or DRIFTNET_VERTEX_CREDENTIALS)GOOGLE_CLOUD_PROJECT· vertex provider: Google Cloud project id (optional when the key file names one)DRIFTNET_JUDGE· Who files each link before the model: jev, rules (free, no model), llm, heuristic, off, or a plugin's judge name
Related
-
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
Official MCP Registry
MCP serversThe MCP project's own registry of public MCP servers, so you can look for a connector before building one.
-
MCP reference servers
MCP serversSmall example servers from the MCP project (filesystem, git, fetch, memory and more) that show how MCP works.
-
Connect MCP servers to Claude Code
MCP serversAnthropic's guide to adding MCP servers to Claude Code, with examples of local and remote servers.
-
Playwright MCP
MCP serversLets an agent drive a real browser: open pages, click, fill in forms and read what's on screen.
claude mcp add playwright npx @playwright/mcp@latest