_ registry / mcp streamable-http · checked 1h ago

wisco-labs

https://api.wiscolabs.dev

Registry code: e8b7faa68b44d42d

api record

Wisco Labs answers questions about open-source package upgrades and security from a continuously collected history of releases, release notes, and OSV vulnerability data. Covers Python (PyPI) and JavaScript (npm). Use upgrade_check with a project's requirements.txt, package-lock.json, or package.json to find malicious packages, versions with known vulnerabilities (with the smallest safe version to move to), and what each upgrade would break, ranked by what to do first. Use vulnerabilities for one exact version, what_changed for one package between two versions, and package_info for latest…

endpoint
https://api.wiscolabs.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 wisco-labs live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is wisco-labs free to use?
Yes — the hub reached it with no key and no payment.
What tools does wisco-labs have?
9 tools: what_changed, types_check, vulnerabilities, upgrade_check, peer_check, wheel_check, native_check, node_check, ….
Is wisco-labs 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
469ms

last good check

priced tools
0

of 9 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 9 tools
9 never probed 0 of 9 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.

  • what_changed unknown never probed

    What breaks, gets removed, is deprecated, or gains a security fix when upgrading one package between two versions, with an overall upgrade risk.

    mcp-tool

    {
  "type": "object",
  "required": [
    "name",
    "from",
    "to"
  ],
  "properties": {
    "to": {
      "type": "string",
      "examples": [
        "3.1.3"
      ],
      "description": "The version you want to upgrade to (use latest_version from package_info if unsure)"
    },
    "from": {
      "type": "string",
      "examples": [
        "2.3.3"
      ],
      "description": "The version you're on now"
    },
    "name": {
      "type": "string",
      "examples": [
        "flask"
      ],
      "description": "Package name, e.g. flask (PyPI) or express or @babel/core (npm)"
    },
    "limit": {
      "type": "string",
      "default": "15",
      "description": "Max items shown per category"
    },
    "ecosystem": {
      "type": "string",
      "default": "PyPI",
      "description": "PyPI or npm"
    }
  }
}
    arguments 41 lines
  • types_check unknown never probed

    For a TypeScript project: which dependencies ship their own type declarations, which need a DefinitelyTyped @types package (and the version that matches the installed library), and which installed @types packages describe a different major version than the library.

    mcp-tool

    {
  "type": "object",
  "required": [
    "requirements"
  ],
  "properties": {
    "requirements": {
      "type": "string",
      "examples": [
        "[email protected]\n@types/[email protected]\[email protected]"
      ],
      "description": "The project's dependencies, including any @types packages: the contents of package-lock.json (best), package.json, or one 'name@version' per line"
    }
  }
}
    arguments 15 lines
  • vulnerabilities unknown never probed

    Is this exact version of a package affected by known security advisories? Returns each vulnerability (with CVE ids and severity), the versions that fix it, and the smallest safe upgrade.

    mcp-tool

    {
  "type": "object",
  "required": [
    "name",
    "version"
  ],
  "properties": {
    "name": {
      "type": "string",
      "examples": [
        "urllib3"
      ],
      "description": "Package name"
    },
    "version": {
      "type": "string",
      "examples": [
        "1.26.18"
      ],
      "description": "The exact version you're using"
    },
    "ecosystem": {
      "type": "string",
      "default": "PyPI",
      "description": "Package ecosystem (OSV naming)"
    }
  }
}
    arguments 28 lines
  • upgrade_check unknown never probed

    Give it a project's dependencies: a requirements.txt or pip freeze output for Python, or a package-lock.json, package.json, or name@version lines for npm. Flags malicious packages and versions with known vulnerabilities (with the smallest safe version to move to, preferring a low-risk patch), then reports what each upgrade breaks, removes, or deprecates, ranked into remove_now / fix_now / no_fix_available / upgrade_first / safe / review / needs_care.

    mcp-tool

    {
  "type": "object",
  "required": [
    "requirements"
  ],
  "properties": {
    "limit": {
      "type": "string",
      "default": "5",
      "description": "Max items shown per category for each package"
    },
    "ecosystem": {
      "type": "string",
      "default": "PyPI",
      "description": "PyPI or npm. A package.json or package-lock.json is recognized as npm automatically."
    },
    "requirements": {
      "type": "string",
      "examples": [
        "flask==2.3.3\nrequests==2.31.0\npydantic==1.10.13"
      ],
      "description": "Python: requirements.txt contents, one 'package==version' per line. npm: the contents of package-lock.json (best), package.json, or one 'name@version' per line. Lines without one exact version are listed but can't be assessed."
    }
  }
}
    arguments 25 lines
  • peer_check unknown never probed

    Before upgrading a core npm package (react, typescript, eslint, vite...), checks every dependency in the project that declares it as a peer dependency: does the installed version accept the new version, and if not, the smallest release that does, with that upgrade's risk. Also checks the new version's own peer requirements against what's installed. Answers the questions behind npm's ERESOLVE errors without running npm.

    mcp-tool

    {
  "type": "object",
  "required": [
    "upgrade",
    "requirements"
  ],
  "properties": {
    "limit": {
      "type": "string",
      "default": "5",
      "description": "Max breaking changes shown for each suggested fix"
    },
    "upgrade": {
      "type": "string",
      "examples": [
        "react@19"
      ],
      "description": "The package and version to upgrade to: react@19 (newest stable 19.x), [email protected] (exact), or react (latest stable)"
    },
    "requirements": {
      "type": "string",
      "examples": [
        "[email protected]\[email protected]\[email protected]"
      ],
      "description": "The project's dependencies: the contents of package-lock.json (best), package.json, or one 'name@version' per line"
    }
  }
}
    arguments 28 lines
  • wheel_check unknown never probed

    For each pinned Python package, whether a prebuilt wheel exists for a target Python version and platform (Windows ARM, Alpine/musl, Linux ARM, macOS, a new Python version). Without one, pip builds from source, which usually fails without a compiler for packages with C extensions. For each that's missing, gives the nearest newer version that has a wheel, with that upgrade's risk.

    mcp-tool

    {
  "type": "object",
  "required": [
    "requirements",
    "python",
    "platform"
  ],
  "properties": {
    "limit": {
      "type": "string",
      "default": "5",
      "description": "Max breaking changes shown for each suggested upgrade"
    },
    "python": {
      "type": "string",
      "examples": [
        "3.13"
      ],
      "description": "Target Python version, e.g. 3.13"
    },
    "platform": {
      "type": "string",
      "examples": [
        "win_arm64"
      ],
      "description": "Target platform: manylinux_x86_64 or manylinux_aarch64 (glibc Linux, e.g. Debian/Ubuntu; assumes glibc 2.36, or give an exact tag like manylinux_2_28_x86_64), musllinux_x86_64 or musllinux_aarch64 (Alpine), win_amd64, win_arm64, win32, macosx_arm64, macosx_x86_64"
    },
    "requirements": {
      "type": "string",
      "examples": [
        "numpy==1.26.4\npsycopg2==2.9.9\nrequests==2.31.0"
      ],
      "description": "requirements.txt contents or pip freeze output, one 'package==version' per line"
    }
  }
}
    arguments 36 lines
  • native_check unknown 1h ago

    Before building on Alpine, Linux ARM, Windows ARM, a Mac or Lambda, checks which npm dependencies contain native code and whether a prebuilt binary exists for the target platform. For those that would compile from source (needing a C/C++ toolchain and Python) or fail, gives the nearest newer version that ships a prebuilt for that platform, with that upgrade's risk.

    mcp-tool

    {
  "type": "object",
  "required": [
    "platform",
    "requirements"
  ],
  "properties": {
    "limit": {
      "type": "string",
      "default": "5",
      "description": "Max breaking changes shown for each suggested fix"
    },
    "platform": {
      "type": "string",
      "examples": [
        "alpine-arm64"
      ],
      "description": "Target platform: os-cpu[-libc], e.g. linux-x64-glibc, linux-arm64-musl, darwin-arm64, win32-arm64; or alpine, alpine-arm64, linux, linux-arm64, lambda, lambda-arm64, windows, win-arm64, mac, mac-intel"
    },
    "requirements": {
      "type": "string",
      "examples": [
        "[email protected]\[email protected]"
      ],
      "description": "The project's dependencies: the contents of package-lock.json (best), package.json, or one 'name@version' per line"
    }
  }
}
    arguments 28 lines
  • node_check unknown 1h ago

    Before moving a project to a new Node.js version (e.g. off Node 20 to 22 or 24), checks each npm dependency's declared Node support (its engines field). For each that doesn't support the target, gives the smallest newer release that does, with that upgrade's risk. Works from a package-lock.json without installing anything.

    mcp-tool

    {
  "type": "object",
  "required": [
    "node",
    "requirements"
  ],
  "properties": {
    "node": {
      "type": "string",
      "examples": [
        "24"
      ],
      "description": "Target Node.js version: a major like 24 (means the latest 24.x) or an exact 22.11.0"
    },
    "limit": {
      "type": "string",
      "default": "5",
      "description": "Max breaking changes shown for each suggested fix"
    },
    "requirements": {
      "type": "string",
      "examples": [
        "[email protected]\[email protected]"
      ],
      "description": "The project's dependencies: the contents of package-lock.json (best), package.json, or one 'name@version' per line"
    }
  }
}
    arguments 28 lines
  • package_info unknown 1h ago

    Latest and latest stable version, repository, release count, and where its release notes come from.

    mcp-tool

    {
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "examples": [
        "flask"
      ],
      "description": "Package name"
    },
    "ecosystem": {
      "type": "string",
      "default": "PyPI",
      "description": "PyPI or npm"
    }
  }
}
    arguments 20 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 e8b7faa68b44d42d.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/e8b7faa68b44d42d/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/e8b7faa68b44d42d/badge.svg)](https://brick.blue/agent/e8b7faa68b44d42d?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
100%

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.