
AgentAvow
Claude connectorCommunityScan any tool, MCP server, or package for a signed safety score before your agent connects to it.
- Tools
- 8
exposed by this connector
Movement
From our daily snapshots over the last 30 days.
Rank by popularity
Rank by trending score
Popularity score
Trending score
In its categories
How this connector compares with others in the same category. Positions are counted within the category, not across the whole directory.
Developer tools477th of 560 by popularity · not ranked by trending score
| # | Connector | Popularity | Trending | 7d |
|---|---|---|---|---|
| 474 | 3,700 | 224places down | ||
| 475 | 3,700 | 135places down | ||
| 476 | 3,700 | 197places down | ||
| 477 | 3,585 | — | ||
| 478 | 3,585 | — | ||
| 479 | 3,585 | — | ||
| 480 | 3,585 | 223places down |
This connector isn’t ranked by trending score, so the category’s top connectors are shown instead.
| # | Connector | Trending | Popularity | 7d |
|---|---|---|---|---|
| 1 | 295,964 | — | ||
| 2 | 265,438 | 56places up | ||
| 3 | 183,079 | 18places up | ||
| 4 | 167,886 | 140places up | ||
| 5 | 165,814 | 44places up | ||
| 6 | 149,997 | 43places up | ||
| 7 | 147,888 | — |
Other206th of 244 by popularity · not ranked by trending score
| # | Connector | Popularity | Trending | 7d |
|---|---|---|---|---|
| 203 | 3,700 | 156places down | ||
| 204 | 3,700 | 197places down | ||
| 205 | 3,700 | — | ||
| 206 | 3,585 | — | ||
| 207 | 3,585 | 223places down | ||
| 208 | 3,585 | 234places down | ||
| 209 | 3,585 | 90places down |
This connector isn’t ranked by trending score, so the category’s top connectors are shown instead.
| # | Connector | Trending | Popularity | 7d |
|---|---|---|---|---|
| 1 | 215,041 | — | ||
| 2 | 209,562 | 15places up | ||
| 3 | 160,987 | 28places up | ||
| 4 | 123,327 | — | ||
| 5 | 99,518 | — | ||
| 6 | 75,999 | 5places down | ||
| 7 | 68,516 | 108places down |
AgentAvow checks a GitHub repo, an MCP server, or an npm / PyPI / crates / Docker / Hugging Face package and returns a 0–100 trust score with a plain safe or needs-review verdict, the findings behind it, and how widely the tool is adopted. Every result is signed with Ed25519 and can be recomputed offline, so you can verify it without trusting us. Read-only, no account. Ask it to scan something before you install or connect it.
Screenshots
Example prompts
- “Scan a package before you install it — and see which ones are AgentAvow Certified”
- “Check whether a package was ever compromised”
- “Scan a repo for risks before your agent connects”
- “Scan a live MCP server's tools for prompt-injection”
Install
claude mcp add --transport http agentavow https://agentavow.com/mcp
Tools
- about_agentavow
- check_interaction_safety
- get_trust_badge
- lookup_identity
- scan_mcp_server
- scan_package
- scan_repo
- verify_trust
Prompts
- agentavow_get_started
- Categories
- Sign-in
- Not required
- Connector URL
- https://agentavow.com/mcp
- Transport
- Streamable HTTP
- Permissions
- Reads public information only — scans public repos, packages, and MCP servers and returns a signed safety score. No access to your accounts, files, conversations, or private data. Anonymous, no login.
- Works with
- Claude, Claude API, Claude Code, Claude Desktop
- Added
- September 15, 2026
- More info



