Open agent watch: 5 well kept projects and the week in numbers, 5 October 2026

Every week our scouts read the public registries where open AI agents and MCP servers are published. They check the things a careful buyer would check before wiring one in: is there a licence, a security policy, a changelog, a valid manifest, and does the endpoint ask who you are. This is what they saw in the week of 5 October 2026 to 11 October 2026.

Projects doing the basics well

These were newly rated, or moved up, and scored in our top two bands. The score is worked out from facts anyone can check. No AI model sets it, and how many stars a project has does not count.

• com.tlsradar/tlsradar (MCP server, MIT licence). Moved from band B to band A, now 99 out of 100. What we could see: a published security policy, a changelog, a valid server.json manifest and an endpoint that asked for authentication when we probed it.
• com.truthifi/mcp (MCP server, MIT licence). Moved from band B to band A, now 99 out of 100. What we could see: a published security policy, a changelog, a valid server.json manifest and an endpoint that asked for authentication when we probed it.
• ai.nyayassist/nyayassist (MCP server, MIT licence). Rated band A, 99 out of 100. What we could see: a published security policy, a changelog, a valid server.json manifest and an endpoint that asked for authentication when we probed it.
• de.fidonis/qdrant-mcp-rbac (MCP server, MIT licence). Rated band A, 99 out of 100. What we could see: a published security policy, a changelog, a valid server.json manifest and a registry entry its own repository confirms.
• com.nextoolsolutions/glpi (MCP server, MIT licence). Rated band A, 98 out of 100. What we could see: a published security policy, a changelog, a valid server.json manifest and an endpoint that asked for authentication when we probed it.

What we held back

605 findings were set aside for a person to look at before we say anything about them: 483 for a low score, 108 for text that reads as an instruction to an AI model rather than to a person, 13 for a name very close to a much better known project and 1 for a published endpoint that points at a private network address. We do not name a project on the strength of a pattern match. A flag is a question, not a verdict.

The week in numbers

• 49,004 projects in the catalogue, 3,383 of them new this week.
• 47,819 have a score so far: 3658 in band A, 26917 in band B, 13696 in band C and 3548 below that. Another 1184 could not be rated because too little could be observed.
• 53 percent of the projects we have read carry a licence we could identify.
• 32 percent of the repositories we read publish a security policy.
• Of 25,106 remote endpoints that answered, 10,432 asked for authentication. For the rest we cannot say either way, because proving it would mean calling someone else's tools, which we do not do.
• 6536 served an A2A Agent Card, and 1515 of those cards followed the specification.

What to do with this

If you are choosing an open agent or MCP server for real work, ask the same questions before you connect it. Who maintains it. What licence it ships under. Where you would report a security problem. Whether its endpoint asks for credentials. Then record the answer in your AI inventory, because the answer changes.

These figures are a hygiene signal worked out from public metadata as of 12 October 2026. They are not a security audit and not a certification. If we have something wrong about your project, tell us and we will fix it or take the listing down.