Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

deadends.dev

PYPI · DEADENDS-DEV · 2 COMPONENTS · SCANNED SEP 20

Structured failure knowledge for AI agents — dead ends, workarounds, error chains

0 this week 80 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security94
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs a script at install time that we could not recognise. It may be perfectly ordinary, but we do not read the published tarball, so we cannot say what it does.Partial
  • 0 of 2 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency45
Schema Quality & AI Usability86
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1136 tokens (~103/item across 11 items; 11 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
  • Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities40
  • Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the deadends.dev MCP server?

deadends.dev runs locally as a PyPI package, launched with uvx deadends-dev. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · deadends-dev

# add to Claude Code
claude mcp add dev-deadends-deadends-dev -- uvx deadends-dev
// .cursor/mcp.json
{
  "mcpServers": {
    "dev-deadends-deadends-dev": {
      "command": "uvx",
      "args": [
        "deadends-dev"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "dev-deadends-deadends-dev": {
      "command": "uvx",
      "args": [
        "deadends-dev"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add dev-deadends-deadends-dev -- uvx deadends-dev
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-deadends-deadends-dev": {
      "type": "local",
      "command": [
        "uvx",
        "deadends-dev"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add dev-deadends-deadends-dev --command uvx --arg deadends-dev
# ~/.hermes/config.yaml
mcp_servers:
  dev-deadends-deadends-dev:
    command: "uvx"
    args: ["deadends-dev"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "dev-deadends-deadends-dev": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "deadends-dev"
      ]
    }
  }
}
# add to Vellum
assistant mcp add dev-deadends-deadends-dev -t stdio -c uvx -a deadends-dev
// mcp.json
{
  "mcpServers": {
    "dev-deadends-deadends-dev": {
      "command": "uvx",
      "args": [
        "deadends-dev"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 18 Sept 26 0
    • Stability: 0.97 → pass security
  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +16
    • Malware scan: unverified → pass security
  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 13 Sept 26 −2
    • Stability: pass → 0.83 functional
  • 12 Sept 26 0
    • Stability: 0.97 → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/deadends-dev@0.9.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Dependencies 2 packages
Packages resolved 2
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 11 exposed · ~1,090 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
batch_lookup ~58

Look up multiple error messages at once. Returns the best match for each error. Use when debugging a chain of errors or analyzing a log with multiple failures.

NameTypeReqDescription
error_messagesarrayyesList of error messages to look up (max 10)

No output schema declared.

No examples provided.

get_country_summary ~77

Get a country-level summary: total entries, domain breakdown, average fix rate, and most-recent updates for the country. Use this to assess coverage for a country before relying on deadends.dev for trip / business / legal planning advice.

NameTypeReqDescription
countrystringyesISO 3166-1 alpha-2 country code, lowercase

No output schema declared.

No examples provided.

get_domain_stats ~63

Get detailed statistics for a domain: error counts, average fix rate, resolvability breakdown, top categories, and confidence levels. Use this to assess how trustworthy deadends.dev data is for a domain.

NameTypeReqDescription
domainstringyesThe domain to get stats for

No output schema declared.

No examples provided.

get_error_chain ~86

Traverse the error transition graph for a specific error. Shows what errors typically follow this one (leads_to), what errors usually precede it (preceded_by), and what errors are frequently confused with it. Use this to diagnose cascading failures and predict what comes next.

NameTypeReqDescription
error_idstringyesThe error ID (domain/slug/env) to get the transition graph for

No output schema declared.

No examples provided.

get_error_detail ~68

Get full details for a specific error by its ID (e.g., 'python/modulenotfounderror/py311-linux'). Includes all dead ends, workarounds, error chain info, and source evidence.

NameTypeReqDescription
error_idstringyesThe error ID (domain/slug/env)

No output schema declared.

No examples provided.

list_error_domains ~78

List all error domains and counts in the deadends.dev database. Covers 51 domains including programming languages, frameworks, infrastructure, ML/AI, culture, safety, medical, legal, and more.

NameTypeReqDescription
sort_bystringSort domains by: 'count' (default, most errors first) or 'name' (alphabetical)

No output schema declared.

No examples provided.

list_errors_by_country ~148

List all country-scoped dead ends for a given country (ISO alpha-2 code, e.g. 'kr', 'jp', 'us', 'de'). Returns visa, banking, legal, cultural, medical, food-safety, emergency, and safety dead ends specific to that jurisdiction. Use this when an AI agent needs jurisdiction-specific knowledge that global LLM training data won't reliably cover.

NameTypeReqDescription
countrystringyesISO 3166-1 alpha-2 country code, lowercase (e.g. 'kr' for Korea, 'jp' for Japan)
domainstringOptional: filter by domain (e.g. 'visa', 'legal', 'culture')

No output schema declared.

No examples provided.

list_errors_by_domain ~82

List all errors in a specific domain with their fix rates. Use this to understand coverage for a domain before relying on it.

NameTypeReqDescription
domainstringyesThe domain to list errors for (e.g., 'python', 'kubernetes')
sort_bystringSort by: 'fix_rate' (default), 'name', or 'confidence'

No output schema declared.

No examples provided.

lookup_error ~168

Match an error message against deadends.dev's database of known errors. Returns dead ends (what NOT to try), workarounds (what works), and error chains (what comes next). Use this BEFORE attempting to fix any error to avoid wasting time on approaches that are known to fail. Covers 51 domains including python, node, docker, git, cuda, typescript, rust, go, kubernetes, terraform, aws, react, java, database, pytorch, tensorflow, and 34 more. Use list_error_domains to see all.

NameTypeReqDescription
error_messagestringyesThe full error message to look up
formatstringResponse format: 'markdown' (default, human-readable) or 'json' (structured, for programmatic use by AI agents)

No output schema declared.

No examples provided.

report_outcome ~145

Report whether a workaround from deadends.dev worked or failed. This feedback improves fix_success_rate and confidence for future users. Call this AFTER applying a workaround to help improve the database. Accepts the error ID, the workaround action you tried, and whether it succeeded.

NameTypeReqDescription
environmentobjectOptional: your environment info (runtime, os, version, etc.)
error_idstringyesThe error ID (domain/slug/env)
notesstringOptional: additional context or notes
successbooleanyesWhether the workaround resolved the error
workaround_actionstringyesThe workaround action string you tried (from the workarounds list)

No output schema declared.

No examples provided.

search_errors ~117

Search errors by keyword across all domains. Unlike lookup_error (which uses regex matching), this does fuzzy keyword search. Use when you have a vague description like 'memory issues' or 'permission denied' rather than an exact error message.

NameTypeReqDescription
domainstringOptional: filter to a specific domain (e.g., 'python', 'docker')
limitintegerMax results to return (default: 10)
querystringyesSearch keywords (e.g., 'memory limit', 'timeout', 'permission denied')

No output schema declared.

No examples provided.

Common questions

What is the deadends.dev MCP server?

deadends.dev is an MCP server listed in the public MCP registry as dev.deadends/deadends-dev. Structured failure knowledge for AI agents, dead ends, workarounds, error chains. This page covers its PyPI package (deadends-dev).

Is the deadends.dev MCP server safe to use?

deadends.dev scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the deadends.dev MCP server expose?

deadends.dev exposes 11 tools: lookup_error, get_error_detail, list_error_domains, search_errors, list_errors_by_domain, and 6 more. Their descriptions and schemas cost roughly 1,090 tokens of context every time the server is loaded.

Is the deadends.dev MCP server still maintained?

deadends.dev is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the deadends.dev MCP server under?

deadends.dev declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.