footon
Turns Claude and Codex JSONL transcripts into sanitized, unlisted links with explicit approval, exposing share management via OAuth-protected MCP endpoints.
README
footon
footon turns Claude and Codex JSONL transcripts into sanitized, unlisted links. Raw transcripts remain local. Only user and assistant prose from an explicitly approved draft can be published.
raw JSONL -> Rust draft + local scanners -> explicit approval -> Cloudflare edge rescan -> unlisted link
The remote MCP endpoint is https://footon.dev/mcp. It uses OAuth 2.1 with
passwordless email sign-in and exposes only share_create, share_list, and
share_revoke.
CLI
cargo install --git https://github.com/douglance/footon footon
footon draft thread.jsonl --title "Public title" --output footon-draft.json
FOOTON_TOKEN=... footon publish footon-draft.json
Drafting makes no network request. Publishing is a separate command and refuses plain HTTP except for localhost tests. See cli/README.md for the full contract.
Development
npm install
npm run check
npm run test:e2e
cargo fmt --check
cargo test
npm run check runs strict TypeScript and Rust linting. The Worker limits
complexity to 8, functions to 45 lines, and files to 220 lines. The Rust crate
denies Clippy all, pedantic, cognitive complexity, large functions,
warnings, and unsafe code across the workspace, all targets, and all features.
The Worker E2E uses Cloudflare's local test harness with isolated D1, KV, and simulated email. It covers dynamic client registration, PKCE authorization, Turnstile's localhost boundary, email capture, magic-link verification, consent without a session cookie, token exchange, and authenticated MCP create, list, and revoke calls. It never sends a real email or writes production data.
Safety boundary
The official CLI combines redact-core with independent credential, key,
connection-string, path, and metadata removal. The Worker validates the exact
footon.share.v2 shape and rejects remaining high-signal secrets and personal
data. No scanner can prove arbitrary text is secret-free, so explicit local
review remains mandatory.
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.