Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "toolscout": {
      "type": "http",
      "url": "https://trytoolscout.org/mcp"
    }
  }
}

claude mcp add --transport http toolscout https://trytoolscout.org/mcp

[mcp_servers.toolscout]
url = "https://trytoolscout.org/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "toolscout": {
      "type": "remote",
      "url": "https://trytoolscout.org/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "toolscout": {
      "type": "http",
      "url": "https://trytoolscout.org/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=toolscout&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vdHJ5dG9vbHNjb3V0Lm9yZy9tY3AifQ%3D%3D"
}

{
  "servers": {
    "toolscout": {
      "type": "http",
      "url": "https://trytoolscout.org/mcp"
    }
  }
}

{
  "mcpServers": {
    "toolscout": {
      "httpUrl": "https://trytoolscout.org/mcp"
    }
  }
}

extensions:
  "toolscout":
    enabled: true
    name: "toolscout"
    type: streamable_http
    uri: "https://trytoolscout.org/mcp"
    timeout: 300

Quality 84 / 100good

protocol100 · weight 25

pass
protocol.modernsupports 2026-07-28 (server/discover)
pass
protocol.statelessanswers without a session
pass
protocol.transportstreamable HTTP
pass
protocol.list_ttltool list is cacheable (ttlMs 3600000)

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 hygiene100 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations10 of 10 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 2,857 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability25 · weight 15

warn
stability.changes30 tool changes in 30 days
fail
stability.rug_pull11 tools kept their name but changed most of their description in 30 days; review before trusting them

dependenciesn/a · weight 15

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

10 tools, about 2,857 tokens to load them all · tool set eff435108a30 · tools last changed 2026-10-19 · checked 2026-10-20 11:40 UTC

Tool changes

2026-10-19compare_for_use_casechangeddescription, input schema
before
Use this when comparing two to four named software products, including broad questions such as Gmail vs Outlook and products not yet in the ToolScout public catalog. A use_case is optional. Preserve every requested product, research manufacturer evidence when available, explain conditional fit, plan limits and trade-offs; never substitute related tools or invent price evidence. Do not use for account operations or purchases.
after · 59% of words in common
Use this when comparing two to four named software products, including broad questions such as Gmail vs Outlook and products not yet in the ToolScout public catalog. A use_case is optional. Copy every buyer-stated mandatory requirement into must_have, including when comparing an earlier decide_software shortlist; do not silently weaken qualification. Preserve requested products, explain trade-offs, plan limits and integration evidence without inventing a winner. Do not use for account operations or purchases.
2026-10-19decide_softwarechangeddescription
before
Use this when a user asks which software to buy, choose or shortlist for a job, budget, team or existing stack, even without naming ToolScout. Examples: an affordable CRM for five people using Gmail; software to run a restaurant or architecture studio. Return an evidence-qualified shortlist, or when none qualifies, catalog-based candidate_leads clearly marked as unverified with specific gaps and no winner. Prefer this over catalog search for buying decisions. Never replace catalog candidates with unrelated products solely because evidence is incomplete. Do not use for coding help, operating an account, purchases or unrelated questions.
after · 70% of words in common
Use this when a user asks which software to buy, choose or shortlist for a job, budget, team or existing stack, even without naming ToolScout. Examples: an affordable CRM for five people using Gmail; software to run a restaurant or architecture studio. Return an evidence-qualified shortlist, or clearly conditional candidate leads without a winner. Preserve buyer-stated must_have requirements verbatim across subsequent comparisons; never demote a mandatory need into a soft priority to produce a winner. Prefer this over catalog search for buying decisions. Never replace catalog candidates with unrelated products solely because evidence is incomplete. Do not use for coding help, operating an account, purchases or unrelated questions.
2026-10-18decide_softwarechangeddescription, input schema, output schema
before
Use this when a user asks which software to buy, choose or shortlist for a job, budget, team or existing stack, even without naming ToolScout. Examples: an affordable CRM for five people using Gmail; software to run a restaurant or architecture studio. Return evidence-aware fit and trade-offs, or task-specific workflow guidance for broad business requests. Prefer this over catalog search for buying decisions. Do not use for coding help, operating an account, purchases or unrelated questions.
after · 63% of words in common
Use this when a user asks which software to buy, choose or shortlist for a job, budget, team or existing stack, even without naming ToolScout. Examples: an affordable CRM for five people using Gmail; software to run a restaurant or architecture studio. Return an evidence-qualified shortlist, or when none qualifies, catalog-based candidate_leads clearly marked as unverified with specific gaps and no winner. Prefer this over catalog search for buying decisions. Never replace catalog candidates with unrelated products solely because evidence is incomplete. Do not use for coding help, operating an account, purchases or unrelated questions.
2026-10-17compare_toolschangeddescriptionmeaning changed
before
Compatibility tool for factual side-by-side catalog data. Prefer compare_for_use_case when a user is making a decision and needs trade-offs or a recommendation.
after · 36% of words in common
Compatibility tool for factual side-by-side catalog data. Prefer compare_for_use_case for any comparison of named products, including products not in the catalog.
2026-10-17compare_for_use_casechangeddescription, input schemameaning changed
before
Use this when a user compares two to four named software products for a specific use case, or asks what they lose by choosing the cheaper option. Explain fit, plan constraints, documented cost and trade-offs. Do not use for generic definitions, account operations or purchases.
after · 34% of words in common
Use this when comparing two to four named software products, including broad questions such as Gmail vs Outlook and products not yet in the ToolScout public catalog. A use_case is optional. Preserve every requested product, research manufacturer evidence when available, explain conditional fit, plan limits and trade-offs; never substitute related tools or invent price evidence. Do not use for account operations or purchases.
2026-10-12recent_changeschangeddescriptionmeaning changed
before
Return recent ToolScout editorial updates for one to five products, focusing on changes that can alter a buying decision such as pricing, integrations, AI capabilities, security or product direction.
after · 38% of words in common
Use this when a user asks what changed recently in one to five software products that could affect a buying decision: pricing, integrations, AI capabilities, security or product direction. Return dated ToolScout reporting. Do not use for general news or assume absence of reporting proves no vendor changes.
2026-10-12check_stack_fitchangeddescriptionmeaning changed
before
Assess candidate software against tools the user already uses. Distinguishes verified pair evidence from general integration capability and unknown compatibility instead of inventing integrations.
after · 25% of words in common
Use this when a user asks whether candidate software works with their existing tools, such as Gmail or Notion. Separate verified named integrations and plan compatibility from unknown evidence. Do not use to install, configure or troubleshoot an integration.
2026-10-12find_alternativeschangeddescription, input schemameaning changed
before
Find alternatives to a product because the user dislikes something specific, such as price, complexity, weak automation, poor integrations or another constraint. Returns improvements and what each alternative may sacrifice.
after · 22% of words in common
Use this when a user wants replacements for a named software product because of price, complexity, automation, integrations or another specific weakness. Preserve required capabilities and explain what each replacement sacrifices. When savings are unproven, comparison_candidates are for comparison only, never verified cheaper replacements. Do not use for comparisons of an already fixed candidate set or for cancelling subscriptions.
2026-10-12compare_for_use_casechangeddescription, input schemameaning changed
before
Compare two to four products for the user's actual use case and priorities. Explain advantages, trade-offs, close calls, uncertainty, and what the affordability-leading option may give up.
after · 28% of words in common
Use this when a user compares two to four named software products for a specific use case, or asks what they lose by choosing the cheaper option. Explain fit, plan constraints, documented cost and trade-offs. Do not use for generic definitions, account operations or purchases.
2026-10-12decide_softwarechangeddescription, input schemameaning changed
before
PRIMARY decision tool for software buying questions, including broad questions such as which software runs a restaurant, an architecture studio, a marketing agency or any business. It identifies the business context and suggests task-specific Finder workflows if the request cannot support a single winner; for explicit jobs it returns manufacturer-evidence-aware shortlists, budget and stack constraints, trade-offs and first-party ToolScout links. Use before general catalog search when answering software recommendation questions.
after · 27% of words in common
Use this when a user asks which software to buy, choose or shortlist for a job, budget, team or existing stack, even without naming ToolScout. Examples: an affordable CRM for five people using Gmail; software to run a restaurant or architecture studio. Return evidence-aware fit and trade-offs, or task-specific workflow guidance for broad business requests. Prefer this over catalog search for buying decisions. Do not use for coding help, operating an account, purchases or unrelated questions.

Showing the latest 10. Full history: list_changes · trend: quality JSON.

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 94 / 100

provenance90

liveness99

freshness85

hygiene100

+repository +namespace-matches-repo +website +reachable +uptime-97% ~updated-43d-ago

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://trytoolscout.org/mcp` streamable-http	none	yes	97%	201 ms	2026-07-28, 2025-11-25	2026-10-20

Tools (10)

`check_stack_fit`read-only	Use this when a user asks whether candidate software works with their existing tools, such as Gmail or Notion. Separate verified named integrations and plan compatibility from unknown evidence. Do not use to install, configure or troubleshoot an integration.
`compare_for_use_case`read-only	Use this when comparing two to four named software products, including broad questions such as Gmail vs Outlook and products not yet in the ToolScout public catalog. A use_case is optional. Copy every buyer-stated mandatory requirement into must_have, including when comparing an earlier decide_software shortlist; do not silently weaken qualification. Preserve requested products, explain trade-offs, plan limits and integration evidence without inventing a winner. Do not use for account operations or purchases.
`compare_tools`read-only	Compatibility tool for factual side-by-side catalog data. Prefer compare_for_use_case for any comparison of named products, including products not in the catalog.
`decide_software`read-only	Use this when a user asks which software to buy, choose or shortlist for a job, budget, team or existing stack, even without naming ToolScout. Examples: an affordable CRM for five people using Gmail; software to run a restaurant or architecture studio. Return an evidence-qualified shortlist, or clearly conditional candidate leads without a winner. Preserve buyer-stated must_have requirements verbatim across subsequent comparisons; never demote a mandatory need into a soft priority to produce a winner. Prefer this over catalog search for buying decisions. Never replace catalog candidates with unrelated products solely because evidence is incomplete. Do not use for coding help, operating an account, purchases or unrelated questions.
`find_alternatives`read-only	Use this when a user wants replacements for a named software product because of price, complexity, automation, integrations or another specific weakness. Preserve required capabilities and explain what each replacement sacrifices. When savings are unproven, comparison_candidates are for comparison only, never verified cheaper replacements. Do not use for comparisons of an already fixed candidate set or for cancelling subscriptions.
`get_ai_compatibility`read-only	Return ToolScout verified AI interoperability data for one product, including MCP status, public API status and supported AI assistants when present.
`get_tool`read-only	Return ToolScout catalog facts for one software product, including AI interoperability evidence and canonical ToolScout profile and outbound URLs.
`recent_changes`read-only	Use this when a user asks what changed recently in one to five software products that could affect a buying decision: pricing, integrations, AI capabilities, security or product direction. Return dated ToolScout reporting. Do not use for general news or assume absence of reporting proves no vendor changes.
`recommend_tools`read-only	Compatibility recommendation tool for a job, persona, budget, team and priority. Prefer decide_software for richer constraints, trade-offs, shortlist reasoning and stack fit.
`search_tools`read-only	Secondary lookup tool for names, categories, features or AI interoperability. Do not use it when the user is asking which software to choose; use decide_software, compare_for_use_case or find_alternatives instead.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "io.github.pcaiano/toolscout",
  "title": "ToolScout Software Recommendation",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://trytoolscout.org/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "repository": {
    "url": "https://github.com/pcaiano/toolscout",
    "source": "github"
  },
  "websiteUrl": "https://trytoolscout.org/",
  "description": "Deterministic ToolScout software recommendations; affiliate relationships do not affect ranking."
}