
Release Alert MCP server
Which MCP servers are Release Alert'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 2026-10-23
- Registry namedev.releasealert/mcpverified in the MCP registry
The registry name sits under releasealert.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-23
- Tools6
- Server calls itselfreleasealert
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-23 the server answered initialize and tools/list without a sign-in. First answer in 121 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 5 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: 5 so far
- Answeredmeasuring5 of the 7 daily checks it takes to print a share
- Median first answer286 ms
- Space in an agent's context≈ 597 tokensthe definitions of all its tools (6), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · get Slack or email alerts when dependencies publish new releases
- not sure · watch npm, PyPI and Docker Hub projects for new versions
- not sure · flag CVEs that match the projects in your stack
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 →
get_cveGet a CVE by its id.
get_projectGet a project by its registry and name.
list_project_cvesList the CVEs that affect a project, newest first.
list_project_releasesList a project's releases, newest first.
list_registriesList the registries Release Alert tracks. A registry's id is what search and the project tools take.
searchSearch for a project by its name, optionally followed by a version, or by its URL, or for a CVE by its id. Each project found carries the registry and name the project tools take.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"releasealert": {
"type": "http",
"url": "https://releasealert.dev/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http releasealert https://releasealert.dev/mcpclaude.ai, ChatGPT and other clients: add https://releasealert.dev/mcp 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.
Cookies
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.