_ registry / mcp streamable-http · checked 2h ago

semverkit

https://semverkit.mike-tusa.workers.dev

Registry code: 3de9a5c84e82cfc4

api record

SemverKit answers Semantic Versioning 2.0.0 questions with the same rules npm uses (node-semver 7), computed instead of guessed. parse_version validates and splits a version; compare_versions gives precedence (-1/0/1) and the change type (major, minor, patch, premajor, prerelease…); check_range tests a version against an npm range (^, ~, x-ranges, hyphen ranges, comparators, ||) and returns the desugared range; resolve_versions sorts up to 200 versions and returns which match a range plus the max/min satisfying and latest stable; bump_version computes the next version like npm version /…

endpoint
https://semverkit.mike-tusa.workers.dev/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is semverkit live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is semverkit free to use?
Yes — the hub reached it with no key and no payment.
What tools does semverkit have?
5 tools: bump_version, check_range, compare_versions, parse_version, resolve_versions.
Is semverkit safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
547ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

inferred, not observed

Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run

_ what it can do 5 tools
5 never probed 0 of 5 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • bump_version unknown 2h ago

    Compute the next version for a release type (major, minor, patch, premajor, preminor, prepatch, prerelease, release), with an optional prerelease id such as alpha, beta or rc, exactly like npm version / semver.inc. Read-only: nothing is published. Same engine as GET /api/bump.

    mcp-tool

    {
  "type": "object",
  "required": [
    "version"
  ],
  "properties": {
    "preid": {
      "type": "string",
      "maxLength": 64,
      "minLength": 1,
      "description": "Prerelease identifier, e.g. \"beta\" (for pre* and prerelease)."
    },
    "release": {
      "enum": [
        "major",
        "minor",
        "patch",
        "premajor",
        "preminor",
        "prepatch",
        "prerelease",
        "release"
      ],
      "type": "string",
      "default": "patch",
      "description": "Release type."
    },
    "version": {
      "type": "string",
      "maxLength": 256,
      "minLength": 1,
      "description": "Current version: a semantic version such as \"1.4.2\", \"v2.0.0\" or \"3.0.0-rc.1+build.5\"."
    }
  },
  "additionalProperties": false
}
    arguments 36 lines
  • check_range unknown 2h ago

    Does a version satisfy an npm-style range (^, ~, x-ranges, hyphen ranges, comparators, || alternatives)? Returns the answer and the range desugared into plain comparators (e.g. ^0.2.3 → >=0.2.3 <0.3.0-0), with a note when npm's prerelease rule is why it fails. Read-only. Same engine as GET /api/satisfies.

    mcp-tool

    {
  "type": "object",
  "required": [
    "version",
    "range"
  ],
  "properties": {
    "range": {
      "type": "string",
      "maxLength": 512,
      "minLength": 1,
      "description": "npm-style range, e.g. \"^1.2.0\", \"~1.4\", \">=1.0.0 <2.0.0\", \"1.2.3 - 2.x\", \"1.x || >=3.0.0-beta.1\"."
    },
    "version": {
      "type": "string",
      "maxLength": 256,
      "minLength": 1,
      "description": "Version to test: a semantic version such as \"1.4.2\", \"v2.0.0\" or \"3.0.0-rc.1+build.5\"."
    },
    "includePrerelease": {
      "type": "boolean",
      "default": false,
      "description": "Let prereleases match any range they fall inside (npm includePrerelease). Default false (npm behaviour)."
    }
  },
  "additionalProperties": false
}
    arguments 27 lines
  • compare_versions unknown 2h ago

    Compare a and b by SemVer precedence (prereleases sort before the release, build metadata ignored). Returns -1, 0 or 1 and the change type from the lower to the higher version (major, minor, patch, premajor, preminor, prepatch, prerelease) exactly like semver.diff. Read-only. Same engine as GET /api/compare.

    mcp-tool

    {
  "type": "object",
  "required": [
    "a",
    "b"
  ],
  "properties": {
    "a": {
      "type": "string",
      "maxLength": 256,
      "minLength": 1,
      "description": "First version: a semantic version such as \"1.4.2\", \"v2.0.0\" or \"3.0.0-rc.1+build.5\"."
    },
    "b": {
      "type": "string",
      "maxLength": 256,
      "minLength": 1,
      "description": "Second version: a semantic version such as \"1.4.2\", \"v2.0.0\" or \"3.0.0-rc.1+build.5\"."
    }
  },
  "additionalProperties": false
}
    arguments 22 lines
  • parse_version unknown never probed

    Validate a version against SemVer 2.0.0 and split it into major, minor, patch, prerelease identifiers and build metadata, with isPrerelease/isStable flags. Read-only. Same engine as GET /api/parse.

    mcp-tool

    {
  "type": "object",
  "required": [
    "version"
  ],
  "properties": {
    "version": {
      "type": "string",
      "maxLength": 256,
      "minLength": 1,
      "description": "Version: a semantic version such as \"1.4.2\", \"v2.0.0\" or \"3.0.0-rc.1+build.5\"."
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
  • resolve_versions unknown never probed

    Sort 1 to 200 versions by SemVer precedence (duplicates removed, invalid ones listed separately) and, if a range is given, return the matching versions plus maxSatisfying / minSatisfying (what npm would install from that list) and the latest stable version. Read-only. Same engine as GET /api/resolve.

    mcp-tool

    {
  "type": "object",
  "required": [
    "versions"
  ],
  "properties": {
    "range": {
      "type": "string",
      "maxLength": 512,
      "minLength": 1,
      "description": "npm-style range, e.g. \"^1.2.0\", \"~1.4\", \">=1.0.0 <2.0.0\", \"1.2.3 - 2.x\", \"1.x || >=3.0.0-beta.1\"."
    },
    "versions": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 256,
        "minLength": 1,
        "description": "Version: a semantic version such as \"1.4.2\", \"v2.0.0\" or \"3.0.0-rc.1+build.5\"."
      },
      "maxItems": 200,
      "minItems": 1,
      "description": "1 to 200 versions."
    },
    "includePrerelease": {
      "type": "boolean",
      "default": false,
      "description": "Let prereleases match any range they fall inside (npm includePrerelease). Default false (npm behaviour)."
    }
  },
  "additionalProperties": false
}
    arguments 32 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 3de9a5c84e82cfc4.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/3de9a5c84e82cfc4/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/3de9a5c84e82cfc4/badge.svg)](https://brick.blue/agent/3de9a5c84e82cfc4?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
90%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.