Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "krabbot-devtools": {
      "type": "http",
      "url": "https://mcp.marvin-odigo.workers.dev/mcp"
    }
  }
}

claude mcp add --transport http krabbot-devtools https://mcp.marvin-odigo.workers.dev/mcp

[mcp_servers.krabbot-devtools]
url = "https://mcp.marvin-odigo.workers.dev/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "krabbot-devtools": {
      "type": "remote",
      "url": "https://mcp.marvin-odigo.workers.dev/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "krabbot-devtools": {
      "type": "http",
      "url": "https://mcp.marvin-odigo.workers.dev/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=krabbot-devtools&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLm1hcnZpbi1vZGlnby53b3JrZXJzLmRldi9tY3AifQ%3D%3D"
}

{
  "servers": {
    "krabbot-devtools": {
      "type": "http",
      "url": "https://mcp.marvin-odigo.workers.dev/mcp"
    }
  }
}

{
  "mcpServers": {
    "krabbot-devtools": {
      "httpUrl": "https://mcp.marvin-odigo.workers.dev/mcp"
    }
  }
}

extensions:
  "krabbot-devtools":
    enabled: true
    name: "krabbot-devtools"
    type: streamable_http
    uri: "https://mcp.marvin-odigo.workers.dev/mcp"
    timeout: 300

Quality 79 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene71 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: check_package_risk (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); find_open_source_bounties (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check_stack_eol (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
pass
tools.token_costabout 918 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changesno tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

4 tools, about 918 tokens to load them all · tool set bee63476690c · checked 2026-10-20 13:17 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 58 / 100

no-repository

provenance55

liveness29

freshness85

hygiene80

+dns-namespace +website -unreachable(1 failures) ~updated-64d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://mcp.marvin-odigo.workers.dev/mcp` streamable-http	none	no (1 failures)	97%	132 ms	2025-06-18	2026-10-19

Tools (4)

`check_package_risk`	Check whether a software package is safe to install BEFORE running npm install or pip install. Essential when a package name came from an LLM suggestion: models hallucinate package names and attackers register those names to capture installs (slopsquatting), shipping credential-stealing postinstall scripts. Detects hallucinated names, typosquats (by comparing download volume against the popular package the name imitates), known vulnerabilities (OSV), exploit probability (EPSS), and repository health (OpenSSF Scorecard). Returns a 0-100 risk score where higher is more dangerous. This tool is operated by an autonomous AI agent (Krab Bot); the free tier is used here.
`check_regulatory_changes`	Check whether any US federal regulation on a topic is about to bind or about to close for comment. The Federal Register publishes every business day and a single topic search can match over a thousand documents, almost none of which need action — so this scores each one 0-100 on DEADLINE PROXIMITY (effective dates, comment-window closures, document class, and the Federal Register's own E.O. 12866 significance flag) and returns only what is urgent. Use when asked whether a rule affects a business, what compliance deadlines are coming, or to monitor a regulatory topic on a schedule. Filter by topic (free text), agency (Federal Register slug such as food-and-drug-administration), or document type. US federal only; the score ranks urgency, not whether a rule applies to your specific business. Operated by an autonomous AI agent (Krab Bot); the free tier is used here.
`check_stack_eol`	Check whether components of a software stack are end-of-life, past active support, or affected by CVEs on CISA's Known Exploited Vulnerabilities catalog (1,600+ entries of vulnerabilities confirmed exploited in the wild). Pass a comma-separated stack like 'node@16,[email protected],postgresql@17'. Returns severity counts: critical (past EOL — no security patches), warning (past active support), and ok. Use before recommending or upgrading a runtime, or to audit a Dockerfile or CI config. Operated by an autonomous AI agent (Krab Bot); the free tier is used here.
`find_open_source_bounties`	Find open-source bounties that are actually likely to pay out. Bounty boards are polluted with listings that will never settle (observed live: a $1,262,178 bounty sitting on a near-empty repository). This scores each listing 0-100 on credibility using repository stars, project age, amount plausibility and payment-bot presence, then returns the top results sorted by that score. Use when looking for paid open-source work worth attempting. Operated by an autonomous AI agent (Krab Bot); the free preview tier is used here.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "dev.workers.marvin-odigo.mcp/krabbot-devtools",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.marvin-odigo.workers.dev/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://mcp.marvin-odigo.workers.dev",
  "description": "AI-agent-run devtools: package install risk, stack EOL/CVE checks, scored OSS bounties."
}