Anti-BullshitSAFE
MCP server for analyzing claims, validating sources, and detecting manipulation using multiple epistemological frameworks
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol server for analyzing claims, validating sources, and detecting manipulation using multiple epistemological frameworks.
Features
The server provides three main tools for detecting and analyzing bullshit:
1. analyze_claim
Analyzes claims using multiple epistemological frameworks:
- Empirical Framework
- Focuses on verifiable evidence
- Evaluates reproducible results
- Cross-references academic and scientific sources
- Assesses methodological rigor
- Responsible Framework
- Evaluates ethical implications
- Assesses community impact
- Considers traditional knowledge
- Validates source credibility
- Harmonic Framework
- Assesses coherence with established knowledge
- Integrates multiple perspectives
- Considers contextual appropriateness
- Evaluates systemic implications
- Pluralistic Framework
- Combines all other frameworks
- Considers multiple ways of knowing
- Evaluates contextual appropriateness
- Assesses practical outcomes
- Checks alignment with community values
2. validate_sources
- Extracts and analyzes cited sources
- Validates credibility and authority
- Cross-references across multiple platforms
- Evaluates methodological soundness
- Checks for conflicts of interest
3. check_manipulation
Detects manipulation tactics including:
- Emotional manipulation
- Social pressure
- False authority
- Artificial scarcity
- Urgency creation
Installation
Prerequisites
- Node.js >= 18.0.0
- npm or yarn
Setup
- Install dependencies:
npm install
- Build the server:
npm run build
- Add to Claude Desktop (MacOS):
{
"mcpServers": {
"anti-bullshit": {
"command": "node",
"args": ["/path/to/anti-bullshit-mcp-server/build/index.js"]
}
}
}Path: ~/Library/Application Support/Claude/claude_desktop_config.json
Or for VSCode extension: Path: `~/Library/Application Support/Code/Us
7b7b171e97d7OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add anti-bullshit-mcp-server -- npx -y [email protected]
{
"mcpServers": {
"anti-bullshit-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
analyze_claim | read | Analyze a claim using multiple epistemological frameworks and suggest validation steps |
check_manipulation | read | Check for manipulation tactics across different cultural contexts |
validate_sources | read | Validate sources and evidence using configured framework |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, axios, zod, @types/node, typescript
Gates applied: no_behavioural_pass.
7b7b171e97d7full audit observations/trust-audit/mcp-server/bmorphism__anti-bullshit.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 7b7b171e97d7 | SAFE | B | 89 | first audit |
Questions
What is the Anti-Bullshit MCP server?
MCP server for analyzing claims, validating sources, and detecting manipulation using multiple epistemological frameworks
What tools does Anti-Bullshit expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Anti-Bullshit safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Anti-Bullshit need?
No credential environment variables were found in its source, so it appears to need none.
How does Anti-Bullshit run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as anti-bullshit-mcp-server at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (7b7b171e97d7), read on 2026-10-09. The repository is watched and re-audited when it changes.