Koskamo

ToolScout MCP

An independent software discovery and decision engine that helps agents choose software based on job-to-be-done, buyer context, and constraints. It provides shortlists, comparisons, and alternatives with recorded prices and manufacturer verification, ensuring affiliate relationships never determine ranking.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

ToolScout MCP logo, by ToolScoutCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by ToolScout
MCP endpoint (Streamable HTTP)
https://trytoolscout.org/mcp
Vendor documentation

What its tools do

4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

4 of 4 have a description · 4 of 4 declare behavior hints · 1 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Find best CRM for a team under a specific budget
  • Compare two software products for a specific workflow
  • Find alternatives to a named software product
  • Check recorded prices and integrations for named products

Source and maintenance

Community listingRegistry 3.3.1
Maintenance checked

Protocol and capabilities

Server
ToolScout 3.3.1
MCP protocol negotiated in check
2025-11-25
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

ToolScout is a read-only software decision engine with four tools. decide_software: which software to choose or buy for a job, budget, team or stack (also broad questions such as software to run a restaurant). compare_software: two to four named products. find_alternatives: replacing a named product for a reason. check_software: prices, AI/MCP support, integrations with existing tools and recent changes for named products. Start your answer from the first text block, which summarises the result. Never invent prices, integrations or a winner, and never substitute a different product. Write tool arguments in English whatever language the user writes in (translate faithfully), put team size in seat_count and quantities such as contacts or emails per month in volumes, send priorities only when the user stated them, and answer the user in their own language. When a result names the plan that holds a quantity, do not recommend a cheaper plan below it. Affiliate compensation never affects ranking. Answer layout: give the answer straight away, with no progress text such as "I will compare"; one call is normally enough, because the result already ranks every qualified product. Prices, plans and integrations in the result are checked against manufacturer documentation on the dates shown. Show fit points as a small text table, never a chart. The only images allowed are the square logo_url icons ToolScout returns, at icon size; otherwise plain product names. Always end the answer, follow-ups included, with the "See on ToolScout" links from the first text block, unchanged.

Tools

4 advertised

decide_software — Decide which software to buy
Advertised by the server during the last successful anonymous check.
Advertised read-only

Use this when the user asks which software to buy for a job, budget, team size or existing tools, e.g. 'a CRM for 5 people'. Returns picks, prices and trade-offs checked against manufacturer docs on the dates shown. End your answer with the ToolScout links it returns. Do not use for coding help or purchases.

decide_software input schema
{
  "type": "object",
  "required": [
    "job"
  ],
  "properties": {
    "job": {
      "type": "string",
      "maxLength": 500,
      "minLength": 3,
      "description": "The concrete job, workflow or outcome the software must support, written in English: translate the buyer's words faithfully whatever language they used, and answer the buyer in their own language. Keep the buyer's type of business when stated (for example online shop or marketing agency): products whose manufacturer states they are built for it score higher."
    },
    "team": {
      "enum": [
        "solo",
        "small",
        "team",
        "large",
        "agency"
      ],
      "type": "string"
    },
    "avoid": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 100,
        "minLength": 1
      },
      "maxItems": 12
    },
    "limit": {
      "type": "integer",
      "default": 3,
      "maximum": 5,
      "minimum": 2
    },
    "budget": {
      "enum": [
        "free",
        "low",
        "mid",
        "high"
      ],
      "type": "string"
    },
    "country": {
      "type": "string",
      "pattern": "^[A-Z]{2}$",
      "description": "ISO 3166-1 alpha-2 country for regional context and price checking. Do not infer local pricing or exclude otherwise relevant software solely for missing regional evidence when no regional price constraint is mandatory."
    },
    "volumes": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 100,
        "minLength": 1
      },
      "maxItems": 6,
      "description": "Quantities the buyer mentioned, in English, e.g. \"1500 marketing contacts\", \"20000 stored contacts\", \"10000 emails per month\". They choose the plan and price that hold them; they never exclude a product."
    },
    "must_have": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 100,
        "minLength": 1
      },
      "maxItems": 12,
      "description": "Only capabilities explicitly required as mandatory by the buyer, not desirable features or assumed sector functions. In English. Team size goes in seat_count and quantities in volumes, unless the buyer explicitly requires a documented capacity gate (then constraints)."
    },
    "priorities": {
      "type": "array",
      "items": {
        "enum": [
          "price",
          "ease",
          "automation",
          "integrations",
          "sales",
          "ai",
          "marketing",
          "seo",
          "research",
          "content",
          "agency",
          "features"
        ],
        "type": "string"
      },
      "maxItems": 6,
      "description": "Only priorities the buyer explicitly stated (for example \"cheap\" or \"easy to use\"). Never add priorities on the buyer's behalf: each one changes the ranking. Leave empty when the buyer stated none.",
      "uniqueItems": true
    },
    "seat_count": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Exact paid seat count used only for explicitly labelled before-tax subscription subtotals."
    },
    "constraints": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 160,
        "minLength": 1
      },
      "maxItems": 12,
      "description": "Only buyer-stated constraints in their own words, including exact budget and billing period when supplied. Do not invent mandatory local prices or integrations."
    },
    "existing_tools": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 100,
        "minLength": 1
      },
      "maxItems": 12,
      "description": "Named software already used by the buyer; for example Gmail and Notion. Do not infer unnamed tools."
    },
    "require_stack_fit": {
      "type": "boolean",
      "description": "When true, every existing tool must have a documented, plan-compatible named integration; otherwise fail closed."
    }
  },
  "additionalProperties": false
}
decide_software output schema
{
  "type": "object",
  "required": [
    "job",
    "shortlist",
    "decision_basis",
    "affiliate_disclosure"
  ],
  "properties": {
    "job": {
      "type": "string"
    },
    "shortlist": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "decision_basis": {
      "type": "object"
    },
    "candidate_leads": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "decision_status": {
      "type": "string"
    },
    "affiliate_disclosure": {
      "type": "string"
    }
  }
}
decide_software annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
compare_software — Compare named software for a use case
Advertised by the server during the last successful anonymous check.
Advertised read-only

Use this when comparing 2 to 4 named products for the buyer's situation, e.g. 'HubSpot or Pipedrive?'. Returns fit, prices and plan limits checked against manufacturer docs on the dates shown. Pass only stated must-haves. End your answer with the ToolScout links it returns. Do not use for unnamed products.

compare_software input schema
{
  "type": "object",
  "required": [
    "tools"
  ],
  "properties": {
    "team": {
      "enum": [
        "solo",
        "small",
        "team",
        "large",
        "agency"
      ],
      "type": "string"
    },
    "tools": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 120,
        "minLength": 1
      },
      "maxItems": 4,
      "minItems": 2,
      "uniqueItems": true
    },
    "budget": {
      "enum": [
        "free",
        "low",
        "mid",
        "high"
      ],
      "type": "string"
    },
    "country": {
      "type": "string",
      "pattern": "^[A-Z]{2}$",
      "description": "ISO country for manufacturer-documented country-specific price comparison."
    },
    "use_case": {
      "type": "string",
      "maxLength": 500,
      "minLength": 3,
      "description": "Optional buyer workflow; omit for a general product-versus-product comparison."
    },
    "must_have": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 100,
        "minLength": 1
      },
      "maxItems": 12,
      "description": "Buyer-stated required capabilities, not preferences; for example automated email follow-ups. Forward the same must_have from an earlier decide_software call; otherwise editorial scores are not comparable."
    },
    "priorities": {
      "type": "array",
      "items": {
        "enum": [
          "price",
          "ease",
          "automation",
          "integrations",
          "sales",
          "ai",
          "marketing",
          "seo",
          "research",
          "content",
          "agency",
          "features"
        ],
        "type": "string"
      },
      "maxItems": 6,
      "description": "Only priorities the buyer explicitly stated (for example \"cheap\" or \"easy to use\"). Never add priorities on the buyer's behalf: each one changes the ranking. Leave empty when the buyer stated none.",
      "uniqueItems": true
    },
    "seat_count": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Exact billed seat count for labelled before-tax per-seat subscription subtotals."
    },
    "existing_tools": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 100,
        "minLength": 1
      },
      "maxItems": 12,
      "description": "Named software already used by the buyer; for example Gmail and Notion. Do not infer unnamed tools."
    },
    "require_stack_fit": {
      "type": "boolean",
      "description": "Require evidence for every named existing-stack integration to award a winner."
    }
  },
  "additionalProperties": false
}
compare_software output schema
{
  "type": "object",
  "required": [
    "use_case",
    "tools",
    "verdict",
    "tradeoffs",
    "affiliate_disclosure"
  ],
  "properties": {
    "tools": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "verdict": {
      "type": "object"
    },
    "use_case": {
      "type": "string"
    },
    "tradeoffs": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "affiliate_disclosure": {
      "type": "string"
    },
    "cheaper_option_analysis": {
      "type": "object"
    }
  }
}
compare_software annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
find_alternatives — Find alternatives to a product
Advertised by the server during the last successful anonymous check.
Advertised read-only

Use this when the buyer wants to leave a named product for a reason, e.g. 'HubSpot costs too much'. Returns alternatives, prices and trade-offs checked against manufacturer docs on the dates shown. End your answer with the ToolScout links it returns. Do not use for a first purchase; use decide_software.

find_alternatives input schema
{
  "type": "object",
  "required": [
    "tool",
    "dislike"
  ],
  "properties": {
    "team": {
      "enum": [
        "solo",
        "small",
        "team",
        "large",
        "agency"
      ],
      "type": "string"
    },
    "tool": {
      "type": "string",
      "maxLength": 120,
      "minLength": 1
    },
    "limit": {
      "type": "integer",
      "default": 3,
      "maximum": 5,
      "minimum": 1
    },
    "budget": {
      "enum": [
        "free",
        "low",
        "mid",
        "high"
      ],
      "type": "string"
    },
    "country": {
      "type": "string",
      "pattern": "^[A-Z]{2}$"
    },
    "dislike": {
      "type": "string",
      "maxLength": 300,
      "minLength": 2
    },
    "use_case": {
      "type": "string",
      "maxLength": 500,
      "minLength": 3
    },
    "must_have": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 100,
        "minLength": 1
      },
      "maxItems": 12,
      "description": "Required capabilities, not preferences; for example automated email follow-ups."
    },
    "seat_count": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1
    },
    "existing_tools": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 100,
        "minLength": 1
      },
      "maxItems": 12,
      "description": "Named software already used by the buyer; for example Gmail and Notion. Do not infer unnamed tools."
    },
    "require_stack_fit": {
      "type": "boolean",
      "description": "Exclude alternatives without evidence for each required stack integration."
    }
  },
  "additionalProperties": false
}
find_alternatives output schema
{
  "type": "object",
  "required": [
    "source",
    "reason",
    "alternatives",
    "affiliate_disclosure"
  ],
  "properties": {
    "reason": {
      "type": "string"
    },
    "source": {
      "type": "object"
    },
    "alternatives": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "affiliate_disclosure": {
      "type": "string"
    }
  }
}
find_alternatives annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
check_software — Check facts about named software
Advertised by the server during the last successful anonymous check.
Advertised read-only

Use this when the buyer asks about 1 to 5 named products: plan prices, free plan, AI or MCP support, integrations with tools in use, or recent changes, e.g. 'Does Pipedrive work with Gmail?'. Facts are checked against manufacturer docs on the dates shown. Do not use for setup or choosing products.

check_software input schema
{
  "type": "object",
  "required": [
    "tools"
  ],
  "properties": {
    "tools": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 120,
        "minLength": 1
      },
      "maxItems": 5,
      "minItems": 1,
      "description": "Product names or ToolScout slugs.",
      "uniqueItems": true
    },
    "budget": {
      "enum": [
        "free",
        "low",
        "mid",
        "high"
      ],
      "type": "string",
      "description": "Use free when only Free-plan integrations count."
    },
    "seat_count": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Paid seats, to show team price subtotals."
    },
    "existing_tools": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 100,
        "minLength": 1
      },
      "maxItems": 12,
      "description": "Software the buyer already uses, to check named integrations; for example Gmail and Notion."
    }
  },
  "additionalProperties": false
}
check_software output schema
{
  "type": "object",
  "required": [
    "tools",
    "missing",
    "changes",
    "affiliate_disclosure"
  ],
  "properties": {
    "tools": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "changes": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "missing": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "affiliate_disclosure": {
      "type": "string"
    }
  }
}
check_software annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
1849 ms
95th percentile latency
1849 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 1849 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http toolscout-mcp https://trytoolscout.org/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add toolscout-mcp --url https://trytoolscout.org/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable toolscout-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "toolscout-mcp": {
      "url": "https://trytoolscout.org/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "toolscout-mcp": {
      "type": "streamableHttp",
      "url": "https://trytoolscout.org/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start toolscout-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "toolscout-mcp": {
      "type": "http",
      "url": "https://trytoolscout.org/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http toolscout-mcp https://trytoolscout.org/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://trytoolscout.org/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "toolscout-mcp": {
      "serverUrl": "https://trytoolscout.org/mcp"
    }
  }
}

Let your agent find its tools

Find servers like ToolScout MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.