notavibe

dev.notavibe/mcpVersion 0.0.1

Ranks open-source projects on maintenance, not popularity. Check your dependencies.

Status

Responds283 msNov 14, 2026, 14:26 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:26 UTC
Latency: 283 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 21:12 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://notavibe.dev/mcpResponds283 msNov 14, 2026, 14:26 UTC

No sign-in

Claude Code

claude mcp add --transport http notavibe https://notavibe.dev/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: notavibe
Remote MCP server URL: https://notavibe.dev/mcp

Cursor

{
  "mcpServers": {
    "notavibe": {
      "url": "https://notavibe.dev/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"notavibe","type":"http","url":"https://notavibe.dev/mcp"}'

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

7 tools

Tools of notavibe
	Description		Read-only	Idempotent	Open world
`check_dependencies`Look up a list of package names on one package registry and return one row per name, in the order given, so the health of a project's dependencies can be read in one call. ecosystem is the package registry the names belong to and accepts only the package registries this catalog admits, currently npm and pypi; any other value is refused as an invalid argument and the refusal names the accepted values. packages lists 1 to 100 names. A list of more than 100 names is refused as an invalid argument and is never cut short. Each name must be a well-formed package name on ecosystem: an npm package name, such as commander or @scope/name, or a PyPI project name, such as requests, compared the way PyPI compares names; a malformed name is refused as an invalid argument that names its position in the list, and nothing is looked up. A name given more than once returns one row, at its first position; PyPI spellings that PyPI compares as the same name count as one name, and the row shows the first spelling given. The request as a whole is limited to 8192 bytes, and a larger request is refused with an error that names the limit. Each name resolves as get_project resolves registry and package: only a package bound to a repository both ways resolves, and a package bound to more than one project does not. A project below the discovery floor that search does not return still resolves. A row for a name that resolves has status matched and a project object: the repository host, numeric id and slug, the project page URL, the claim state, the five health-signal bands, each with its status, source and fetch date, and the signals_unavailable and stale flags. Every other row has status not_in_catalog and carries only the name, whatever the reason the name did not resolve. Rows are never sorted by health, and the response carries no score, rank, total or person-derived count. The names are used only to answer the call: this server does not store or log them, and its usage analytics record the r	Look up a list of package names on one package registry and return one row per name, in the order given, so the health of a project's dependencies can be read in one call. ecosystem is the package registry the names belong to and accepts only the package registries this catalog admits, currently npm and pypi; any other value is refused as an invalid argument and the refusal names the accepted values. packages lists 1 to 100 names. A list of more than 100 names is refused as an invalid argument and is never cut short. Each name must be a well-formed package name on ecosystem: an npm package name, such as commander or @scope/name, or a PyPI project name, such as requests, compared the way PyPI compares names; a malformed name is refused as an invalid argument that names its position in the list, and nothing is looked up. A name given more than once returns one row, at its first position; PyPI spellings that PyPI compares as the same name count as one name, and the row shows the first spelling given. The request as a whole is limited to 8192 bytes, and a larger request is refused with an error that names the limit. Each name resolves as get_project resolves registry and package: only a package bound to a repository both ways resolves, and a package bound to more than one project does not. A project below the discovery floor that search does not return still resolves. A row for a name that resolves has status matched and a project object: the repository host, numeric id and slug, the project page URL, the claim state, the five health-signal bands, each with its status, source and fetch date, and the signals_unavailable and stale flags. Every other row has status not_in_catalog and carries only the name, whatever the reason the name did not resolve. Rows are never sorted by health, and the response carries no score, rank, total or person-derived count. The names are used only to answer the call: this server does not store or log them, and its usage analytics record the r	Not declared	Not declared	Not declared	Not declared
`compare_projects`Return the public profiles of two catalog projects side by side, identified by host and two owner/repo slugs; a former slug resolves as it does for get_project. The response presents each project's facts and health bands; it draws no conclusion and names no winner. What each band means is published on the catalog's methodology page (/methodology) and returned by get_methodology. The pair is refused when either slug matches no project in this catalog or names a project with insufficient measured signals, or when both name the same repository; the refusal names the argument, a or b, at fault. A project on gitlab is published with its health signals unavailable, so it is refused here and is returned only by get_project. Read-only. Serves catalog schema v1.	Return the public profiles of two catalog projects side by side, identified by host and two owner/repo slugs; a former slug resolves as it does for get_project. The response presents each project's facts and health bands; it draws no conclusion and names no winner. What each band means is published on the catalog's methodology page (/methodology) and returned by get_methodology. The pair is refused when either slug matches no project in this catalog or names a project with insufficient measured signals, or when both name the same repository; the refusal names the argument, a or b, at fault. A project on gitlab is published with its health signals unavailable, so it is refused here and is returned only by get_project. Read-only. Serves catalog schema v1.	Not declared	Not declared	Not declared	Not declared
`get_lists`List the public curated lists in the notavibe catalog, or return the public members of one list identified by owner handle and list slug. Only public lists and their publishable members are returned; a list that does not exist or is not public returns {"found": false, "subject": "list"}. handle and slug are given together or not at all; one without the other is refused as an invalid argument. Read-only. Serves catalog schema v1.	List the public curated lists in the notavibe catalog, or return the public members of one list identified by owner handle and list slug. Only public lists and their publishable members are returned; a list that does not exist or is not public returns {"found": false, "subject": "list"}. handle and slug are given together or not at all; one without the other is refused as an invalid argument. Read-only. Serves catalog schema v1.	Not declared	Not declared	Not declared	Not declared
`get_methodology`Return what each of the catalog's five health signals measures and, for each signal, its bands in order, each with a one-line meaning and its published cut-point. The text is the same as the catalog's methodology page (/methodology), built from the same source. Takes no arguments. Reads no catalog data and returns no project. Read-only. Serves catalog schema v1.	Return what each of the catalog's five health signals measures and, for each signal, its bands in order, each with a one-line meaning and its published cut-point. The text is the same as the catalog's methodology page (/methodology), built from the same source. Takes no arguments. Reads no catalog data and returns no project. Read-only. Serves catalog schema v1.	Not declared	Not declared	Not declared	Not declared
`get_more_tools`Records a description of a capability missing from the other tools of this server, for the maintainers of this server. The description is stored by an analytics service. It returns an acknowledgement and adds no tools: every tool of this server is already listed. Reads no catalog data. Serves catalog schema v1.	Records a description of a capability missing from the other tools of this server, for the maintainers of this server. The description is stored by an analytics service. It returns an acknowledgement and adds no tools: every tool of this server is already listed. Reads no catalog data. Serves catalog schema v1.	Not declared	Not declared	Not declared	Not declared
`get_project`Return the public profile of one catalog project, identified either by host and an owner/repo slug or a numeric repository id, or by registry and package, a package name on a package registry. host and exactly one of slug or id are required unless registry and package are given; a call missing them, giving both slug and id, or giving a host other than github or gitlab or a slug that is a URL or ends in a slash is refused as an invalid argument and names what is wrong. registry and package are given together and without host, slug or id. registry accepts only the package registries this catalog admits, currently npm and pypi; any other value is refused as an invalid argument and the refusal names the accepted values. package must be a well-formed package name on registry: an npm package name, such as commander or @scope/name, or a PyPI project name, such as requests; a malformed name is refused as an invalid argument. A PyPI name is compared the way PyPI compares names: letter case is ignored, and any run of -, _ and . counts as a single -. A package resolves only when it is bound to a repository both ways: the repository's package.json names the npm package, or its root pyproject.toml names the PyPI package, and the package names the repository as its source. A pyproject.toml in a subdirectory does not count, and a PyPI package binds once its first stable release that names the repository is at least 90 days old and every stable release that names a repository names this one. For npm, the package.json is the repository's root one unless it is marked private, or one in a workspace package directory; a package named only by a workspace package.json binds once its first stable release that names the repository is at least 90 days old and every stable release that names a repository names this one. A verified signed publish attestation for the package's newest stable version that names the repository also binds it, under the same age rule. A package that is not bound to	Return the public profile of one catalog project, identified either by host and an owner/repo slug or a numeric repository id, or by registry and package, a package name on a package registry. host and exactly one of slug or id are required unless registry and package are given; a call missing them, giving both slug and id, or giving a host other than github or gitlab or a slug that is a URL or ends in a slash is refused as an invalid argument and names what is wrong. registry and package are given together and without host, slug or id. registry accepts only the package registries this catalog admits, currently npm and pypi; any other value is refused as an invalid argument and the refusal names the accepted values. package must be a well-formed package name on registry: an npm package name, such as commander or @scope/name, or a PyPI project name, such as requests; a malformed name is refused as an invalid argument. A PyPI name is compared the way PyPI compares names: letter case is ignored, and any run of -, _ and . counts as a single -. A package resolves only when it is bound to a repository both ways: the repository's package.json names the npm package, or its root pyproject.toml names the PyPI package, and the package names the repository as its source. A pyproject.toml in a subdirectory does not count, and a PyPI package binds once its first stable release that names the repository is at least 90 days old and every stable release that names a repository names this one. For npm, the package.json is the repository's root one unless it is marked private, or one in a workspace package directory; a package named only by a workspace package.json binds once its first stable release that names the repository is at least 90 days old and every stable release that names a repository names this one. A verified signed publish attestation for the package's newest stable version that names the repository also binds it, under the same age rule. A package that is not bound to	Not declared	Not declared	Not declared	Not declared
`search_projects`Search the notavibe catalog of open-source projects. The query matches project name, project description, and the category, ecosystem, kind, runtime, license_family and capabilities vocabulary facets; free-form repository topics are not matched. capabilities names what a project does, such as http-client, logging or database. Its values come from a fixed list kept by this catalog, and a project carries one only when a tag mapped to it is declared on the project's GitHub repository, or on an npm or PyPI package bound to that repository both ways: the repository's package.json names the npm package, or its root pyproject.toml names the PyPI package, and the package names the repository as its source. Most projects carry no capabilities. A query that is exactly a project's repository name, that name without a .js or .ts suffix or without its dots, or the name of an npm or PyPI package bound to the project, also matches that project. A facet match adds a project to the results and does not affect its position in them: results are ordered first by an exact match of the whole query to a bound npm or PyPI package name, then to one of those repository names, then by how closely the query matches name and description, then by published health signals. Every word of the query must match. A project's description is generated from its facets until its maintainer claims it and writes their own, so a query describing what a project does, such as "http router" or "date parsing", matches only where those words appear in a project name, in a claimed description, or among the words a facet value matches; a project name or a category, kind or ecosystem word is what a generated entry reliably matches. The catalog currently covers two ecosystems: javascript-typescript and python. Its coverage of each is partial: it does not yet hold every JavaScript or TypeScript project published to npm, or every Python project published to PyPI. category, ecosystem, kind, runtime, license_family and c	Search the notavibe catalog of open-source projects. The query matches project name, project description, and the category, ecosystem, kind, runtime, license_family and capabilities vocabulary facets; free-form repository topics are not matched. capabilities names what a project does, such as http-client, logging or database. Its values come from a fixed list kept by this catalog, and a project carries one only when a tag mapped to it is declared on the project's GitHub repository, or on an npm or PyPI package bound to that repository both ways: the repository's package.json names the npm package, or its root pyproject.toml names the PyPI package, and the package names the repository as its source. Most projects carry no capabilities. A query that is exactly a project's repository name, that name without a .js or .ts suffix or without its dots, or the name of an npm or PyPI package bound to the project, also matches that project. A facet match adds a project to the results and does not affect its position in them: results are ordered first by an exact match of the whole query to a bound npm or PyPI package name, then to one of those repository names, then by how closely the query matches name and description, then by published health signals. Every word of the query must match. A project's description is generated from its facets until its maintainer claims it and writes their own, so a query describing what a project does, such as "http router" or "date parsing", matches only where those words appear in a project name, in a claimed description, or among the words a facet value matches; a project name or a category, kind or ecosystem word is what a generated entry reliably matches. The catalog currently covers two ecosystems: javascript-typescript and python. Its coverage of each is partial: it does not yet hold every JavaScript or TypeScript project published to npm, or every Python project published to PyPI. category, ecosystem, kind, runtime, license_family and c	Not declared	Not declared	Not declared	Not declared

Details

Registry status: Active
Published: Oct 28, 2026
Updated: Oct 28, 2026
Website: https://notavibe.dev/⁠ (opens in a new tab)
Repository: Not given
Categories (suggested): Project managementSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing