AgentAvow
Claude connectorCommunityCheck any tool, MCP server, or package before your agent connects: Safe, Review, or Do not connect.
AgentAvow tells you whether a tool is safe for your AI agent to connect to, before it connects.
Point it at a GitHub repo, an npm, PyPI, crates, Docker or Hugging Face package, or a live MCP server. Every result leads with one of three answers and the reason behind it:
- Safe to connect: nothing blocking was found.
- Review before you connect: a high-severity finding, a published advisory for that version, a deprecated package, or a low trust score.
- Do not connect: a critical finding, a known-malicious dependency, or a planted test credential leaving our sandbox.
"Certified" marks tools that also passed every provenance check.
Under the answer sit two scores: a 0 to 100 trust score built from the findings, and an adoption score built from real usage (downloads, stars, installs). Each finding says where it is and how to fix it. Packages and MCP servers can also be run in a locked-down sandbox to see what they actually do: network calls, file writes, and whether planted credentials stay put.
Every result is signed (Ed25519) and can be recomputed offline against our public keys, so you can check it without trusting us.
Read-only. No account. Ask it to check a tool before you install or connect it.
AgentAvow is #3,918 of 11,065 Claude connectors by popularity, down 135 places in a week. It is #3,629 of 4,156 by trending score, down 290 places in a week.
- 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
3 listing changes logged · latest Oct 10: Description, One-liner. See what changed
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 tools731st of 1,980 by popularity · 613th of 728 by trending score
| # | Connector | Popularity | Trending | 7d |
|---|---|---|---|---|
| 729 | 6,426 | 8,154 #574 | 220places down | |
| 730 | 6,426 | 5,053 #661 | 312places down | |
| 731 | AgentAvowThis page | 6,409 | 6,916 #613 | 135places down |
| 732 | 6,409 | — | 220places down | |
| 733 | 6,409 | — | 516places up |
| # | Connector | Trending | Popularity | 7d |
|---|---|---|---|---|
| 611 | 6,919 | 6,426 #727 | 819places down | |
| 612 |  Swath API | 6,919 | 9,562 #286 | 728places down |
| 613 | AgentAvowThis page | 6,916 | 6,409 #731 | 290places down |
| 614 |  AgentGrid.io | 6,916 | 10,033 #246 | 242places down |
| 615 |  AgentMart Site Check | 6,899 | 7,313 #551 | 2,154places down |
Also on other marketplaces
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
- Sponsorship
- Promote this connector