Faultline
Check the key factual claims in AI output against live web sources
- Pricing
- Freemium
- Platforms
- API, CLI, Web
- Runs
- Remotely
- Version
- 0.12.1
- Listing updated
- 3 days ago
About Faultline
Faultline is a freemium MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.
Faultline splits AI-written text into claims, picks the most important factual ones, and checks each against sources it finds on the live web. A normal scan checks up to 8 claims and returns a risk band plus a list of anything it could not verify. A deep scan covers every factual claim. It can fail a CI build on the result.
The MCP server exposes a single tool, verify_claims, and needs an API key in an x-api-key header. A claim is billed only when Faultline returns a verdict backed by a source. Unverified claims and provider errors are free. The README labels the project alpha and reports 0.755 balanced accuracy on 200 human-labelled Factcheck-Bench claims.
Scans run on Gemini against sources found with Parallel, with multi-model consensus using OpenAI and Anthropic reserved for Enterprise. Hosted scans use Faultline's own provider keys. The API also produces governance records such as a risk register export and human sign-off records.
Install
Run in a terminal
claude mcp add --transport http faultline https://faultline-api.fly.dev/mcpAdd to Settings → Connectors → Add custom connector
https://faultline-api.fly.dev/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"faultline": {
"url": "https://faultline-api.fly.dev/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"faultline": {
"type": "http",
"url": "https://faultline-api.fly.dev/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"faultline": {
"serverUrl": "https://faultline-api.fly.dev/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"faultline": {
"type": "http",
"url": "https://faultline-api.fly.dev/mcp"
}
}
}Tools this server provides (1)
Taken from the project documentation; the running server may differ.
- verify_claims
- Extracts claims from text and checks them against live sources.
What it does
- Claim extraction
- Breaks AI output into atomic factual claims.
- Live-source checking
- Verifies the most important claims against current web sources.
- Risk band
- Returns a risk level and a list of claims it could not verify.
- Deep scan
- Checks every factual claim instead of the top few.
- CI gating
- Can fail a build based on the result.
- Governance records
- Risk register, audit log manifest and human sign-off via the API.
Good for
- Catch fabricated citations before publishing
- Fact-check an agent's report in a pipeline
- Gate pull requests that include AI-written docs
- Produce an audit trail for reviewed AI output
- Verify claims in a draft with a quick scan
Pricing
Freemium, from $10 a month
Free 5 scans/month; Personal $19; Pro $49; API key $10/mo plus $0.10 per billed claim
Prices change. Check faultline.nxtg.ai before you buy.
Faultline FAQ
What does a scan cost?
Free gives 5 scans a month, Personal is $19 for 100, and Pro is $49 for 500. The API key is $10 a month with 100 billed claims, then $0.10 each.
When is a claim billed?
Only when Faultline returns a verdict backed by a source it found.
How accurate is it?
The README reports 0.755 balanced accuracy on 200 human-labelled claims, and the project is in alpha.
Does it store my text?
The engine does not write scanned text to storage; signed-in scans are saved to your own history for 2 years.
Is Faultline free?
Faultline has a free plan, with paid plans for more usage or features. Paid plans start at $10 a month.
How do I add Faultline to Claude Code?
Run this command in your terminal: claude mcp add --transport http faultline https://faultline-api.fly.dev/mcp
What are the best alternatives to Faultline?
The closest alternatives to Faultline are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Faultline

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools