cred-1SAFE
CRED-1: Open, reproducible domain credibility dataset for automated pre-bunking of online misinformation. TypeScript library, CLI & MCP server. Check any news source's reliability from terminal, code, or AI agents. CC BY 4.0, DOI-citable.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://doi.org/10.5281/zenodo.18769459) [](https://github.com/aloth/cred-1/actions/workflows/publish.yml) [](https://creativecommons.org/licenses/by/4.0/) [](https://www.npmjs.com/package/@aloth/cred1) [](https://www.npmjs.com/package/@aloth/cred1) [](https://calver.org/) [](https://github.com/aloth/cred-1/issues/new?template=domain-report.yml)
CRED-1 is an open, reproducible domain-level credibility dataset combining multiple openly-licensed source lists with computed enrichment signals. It provides credibility scores for 2,600+ domains (exact count in the latest release) known to publish mis/disinformation, conspiracy theories, or other unreliable content. Community members can report missing domains for inclusion.
🎓 Presented at ACM WebSci 2026 (Braunschweig). Landing page: aloth.github.io/agentic-ai-information-integrity/cred-1.
🤖 MCP-ready — query domain credibility directly from Claude Desktop, Cursor & Windsurf, or any MCP-compatible agent. Jump to setup ↓
Paper: A. Loth, M. Kappes, and M.-O. Pahl, "CR
c3006440ad43OBSERVED · 2026-10-10Connect
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. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add cred1 --env GOOGLE_API_KEY=${GOOGLE_API_KEY} -- npx -y @aloth/[email protected]{
"mcpServers": {
"cred1": {
"command": "npx",
"args": [
"-y",
"@aloth/[email protected]"
],
"env": {
"GOOGLE_API_KEY": "${GOOGLE_API_KEY}"
}
}
}
}Exposed tools (5)
5 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
batch_check | read | Check multiple domains at once (max 100). Returns an array of results with the same |
check_domain | read | Check a single domain\ |
get_categories | read | List all credibility categories with their descriptions, typical score ranges, and domain counts from the dataset. |
get_stats | read | Get summary statistics for the CRED-1 dataset: total domain count, per-category breakdown, and dataset version. |
search_domains | read | Search for domains matching a substring or regex pattern. Useful for discovering all |
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 | WARN |
| 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
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
print(f" API key: ...{api_key[-6:]}")@modelcontextprotocol/sdk, chalk, commander, @types/node, tsx, typescript
Gates applied: no_behavioural_pass.
c3006440ad43full audit observations/trust-audit/mcp-server/aloth__cred-1.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 |
|---|---|---|---|---|---|
| 2026-10-10 | c3006440ad43 | SAFE | B | 89 | first audit |
Questions
What is the cred-1 MCP server?
CRED-1: Open, reproducible domain credibility dataset for automated pre-bunking of online misinformation. TypeScript library, CLI & MCP server. Check any news source's reliability from terminal, code, or AI agents. CC BY 4.0, DOI-citable.
What tools does cred-1 expose?
5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is cred-1 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 cred-1 need?
It reads GOOGLE_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does cred-1 run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @aloth/cred1 at 2026.10.8.
How current is this page?
The grade is for one exact copy of the source (c3006440ad43), read on 2026-10-10. The repository is watched and re-audited when it changes.