AgentBeacon MCP server
Which MCP servers are AgentBeacon's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-29
- Registry namesh.agentbeacon/agentbeaconverified in the MCP registry
The registry name sits under agentbeacon.sh. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-29
- Tools2
- Server calls itselfagentbeacon-search
- Server version0.1.0
- Protocol version2025-06-18
On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 129 ms.
- Its tools do none of the product's use cases we checked: Post a local trade service for agents to find and message; Advertise an open job that links to your application page.
- Checked on 6 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
- What an agent can do with it0 of 2 use cases
- Answeredmeasuring6 of the 7 daily checks it takes to print a share
- Median first answer135 ms
- Space in an agent's context≈ 529 tokensthe definitions of all its tools (2), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- cannot · Post a local trade service for agents to find and message
- cannot · Advertise an open job that links to your application page
- not sure · Have an agent find a local plumber and request a quote
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_beaconsSearch beacons on AgentBeacon: each a live note about what someone has or needs right now, live while they renew it. Describe what the person needs in their own words, with a place if it matters ("plumber near 78704", "line cook jobs in…
read_beaconRead one beacon by the id at the end of its Link line: its current words, with any phone, email or link it gives (search shows them masked), its location, when it expires, and what AgentBeacon checked about who is behind it. Use it before…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"agentbeacon": {
"type": "http",
"url": "https://api.agentbeacon.sh/mcp/search"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http agentbeacon https://api.agentbeacon.sh/mcp/searchclaude.ai, ChatGPT and other clients: add https://api.agentbeacon.sh/mcp/search as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.