Koskamo

AI-first company MCP

This MCP server provides read-only access to an evidence-rated database of AI adoption practices, company cases, claim checks, and assessments. It allows AI assistants to query rated evidence, verify statistics, and review vendor promises using sources linked to primary data.

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.

AI-first company MCP logo, by AI-first companyVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by AI-first company
MCP endpoint (Streamable HTTP)
https://mcp.ai-first.company/mcp
Vendor documentation

What you can do with it

  • Check if a widely quoted AI statistic is accurate and find its source.
  • Review a company's AI rollout plan against rated best practices.
  • Find named company cases and outcomes for specific AI use cases.
  • Prepare a board brief on AI adoption readiness and measured results.

Source and maintenance

Vendor evidenceRegistry 0.3.6
mcp-registry: company.ai-first/evidence@0.3.6Project website

Protocol and capabilities

Server
ai-first-company-evidence 0.3.6
MCP protocol
2025-06-18
Tools
10 advertised
Resources
7 advertised
Resource templates
0 advertised
Prompts
1 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  },
  "prompts": {
    "listChanged": true
  },
  "resources": {
    "listChanged": true
  }
}

Server-provided instructions

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

Evidence about adopting AI in a business, from ai-first.company: rated practices, company cases with their outcomes, checked figures, studies and readiness assessments. Move through it by menus: call start (or the task tool that fits the question), open the part of the map that fits (open, with the arguments the menus show), then call get_evidence with the ids of the rows you pick. Every list shows all its rows or splits them into a menu, so nothing is hidden; choose by meaning, whatever the language of the question. Full records list related ids (studies, cases, practices) you can fetch to follow a lead. State figures, ratings, verdicts and findings only from get_evidence, and cite the links it returns. If nothing fits, say so: do not fill the gap from memory. Never ask the user to call a tool or show them the ids. Answer the user in their language.

Tools

10 advertised

start — Start here: the map of the evidence
Advertised by the server during the last successful anonymous check.
Advertised read-only

Start here for any question about adopting AI in a company: the map of the ai-first.company evidence. Returns the company cases by the kind of work AI was used for (customer service, legal work, office assistant and others), the six themes (with counts of practices, cases and studies), the claim checks of widely repeated AI statistics, the groups of other figures, the company cases by outcome, the assessments by kind, and what each filter value and rating means. Then open the part that fits and fetch records with get_evidence.

start input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
start annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
open — Open one part of the evidence map
Advertised by the server during the last successful anonymous check.
Advertised read-only

Open one part of the evidence map: a list (practices, cases, studies, figures, claim-checks, assessments) with filters such as theme, outcome, industry, company size, stage, priority, figure group (line) or assessment kind. Returns every matching row in one line with its id, or, when there are more than 25, a menu splitting them by the next filter, with counts. Use the arguments the menus show. Then fetch the rows you pick with get_evidence.

open input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "list"
  ],
  "properties": {
    "kind": {
      "type": "string",
      "maxLength": 500,
      "description": "Figures: the kind of number, e.g. measured-in-a-study or self-reported. Assessments: the kind key from start, e.g. readiness-surveys."
    },
    "line": {
      "type": "string",
      "maxLength": 500,
      "description": "Figures only: the group key from start, e.g. time-freed or running-cost."
    },
    "list": {
      "enum": [
        "practices",
        "cases",
        "claim-checks",
        "figures",
        "studies",
        "assessments"
      ],
      "type": "string",
      "description": "Which list: practices, cases, studies, figures, claim-checks or assessments."
    },
    "size": {
      "type": "string",
      "maxLength": 500,
      "description": "Company size band: micro-small, medium, mid-market, enterprise (1–49, 50–249, 250–999, 1,000+ employees). Or pass employees instead."
    },
    "task": {
      "type": "string",
      "maxLength": 500,
      "description": "Cases only: the kind of work AI was used for, a task key from start, e.g. customer-service-and-support or legal-research-drafting-and-filings."
    },
    "stage": {
      "enum": [
        "explore",
        "adopt",
        "redesign",
        "run"
      ],
      "type": "string",
      "description": "How far the company is: explore, adopt, redesign or run."
    },
    "theme": {
      "type": "string",
      "maxLength": 500,
      "description": "A theme key from start, e.g. governance-and-risk or people-and-skills."
    },
    "outcome": {
      "enum": [
        "measured",
        "company-reported",
        "went-wrong",
        "walked-back"
      ],
      "type": "string",
      "description": "Cases with this outcome: measured, company-reported, went-wrong or walked-back."
    },
    "industry": {
      "enum": [
        "professional-services",
        "agencies",
        "ecommerce-retail",
        "manufacturing",
        "other"
      ],
      "type": "string",
      "description": "Cases in this industry: professional-services, agencies, ecommerce-retail, manufacturing, or other (none of the four, e.g. banks, airlines, public bodies). Practices apply to all industries."
    },
    "priority": {
      "enum": [
        "do first",
        "do next",
        "do later"
      ],
      "type": "string",
      "description": "Practices with this priority."
    },
    "employees": {
      "type": "integer",
      "maximum": 10000000,
      "description": "Number of employees, e.g. 120.",
      "exclusiveMinimum": 0
    },
    "free_only": {
      "type": "boolean",
      "description": "Assessments only: free to use."
    }
  }
}
open annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_evidence — Get full evidence records by id
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get the full records for ids from the menus and lists (such as "case:klarna-ai-customer-service" or "claim-check:mit-95-percent-of-ai-pilots-fail"): figures, ratings, verdicts, caveats, primary sources, the ai-first.company link, and the ids of related studies, cases and practices to follow. Up to 20 ids per call. Quote and cite only from what this returns.

get_evidence input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "ids"
  ],
  "properties": {
    "ids": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 200,
        "minLength": 1
      },
      "maxItems": 20,
      "minItems": 1,
      "description": "Ids as the menus and lists give them, e.g. [\"case:klarna-ai-customer-service\", \"practice:ask-ai-vendors-for-proof\"]."
    }
  }
}
get_evidence annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
check_ai_figure — Check an AI statistic before quoting it
Advertised by the server during the last successful anonymous check.
Advertised read-only

Before quoting an AI statistic (e.g. '95% of AI pilots fail', 'only 13% of companies are ready for AI'), check where it comes from, who was asked and what it covers. Returns every claim check of a widely repeated statistic and the groups of other figures; fetch the matching claim check, or open the group the figure belongs to. Use it for figures from surveys, reports and the press. For a claim a vendor makes about its own product, use check_vendor_claim.

check_ai_figure input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
check_ai_figure annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
check_vendor_claim — Check a vendor’s AI claim
Advertised by the server during the last successful anonymous check.
Advertised read-only

Check a claim made by an AI vendor or consultant, such as '30% productivity gain', 'cuts support costs by 40%' or 'our agents replace 700 staff'. Returns the questions to ask the vendor, the claim checks, the groups of figures and the company cases by the kind of work AI was used for, so you can find the same result and companies that tried the same kind of tool. Use it whenever someone selling or proposing AI quotes a result. For a statistic from the press or a report, use check_ai_figure.

check_vendor_claim input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
check_vendor_claim annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
review_ai_transformation_plan — Review an AI plan or business case
Advertised by the server during the last successful anonymous check.
Advertised read-only

Review an AI transformation proposal, business case or rollout memo, for example before it goes to a board. Returns the do-first practices for the company’s size as a checklist, each with its evidence rating and wording that may show it, and how to find similar cases. You read the plan and decide for each practice whether the plan commits to it, rules it out or leaves it out. Pass the size and industry; the plan itself stays with you. For one figure in the plan, use check_ai_figure.

review_ai_transformation_plan input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "size": {
      "type": "string",
      "maxLength": 500,
      "description": "Company size band: micro-small, medium, mid-market, enterprise (1–49, 50–249, 250–999, 1,000+ employees). Or pass employees instead."
    },
    "industry": {
      "enum": [
        "professional-services",
        "agencies",
        "ecommerce-retail",
        "manufacturing"
      ],
      "type": "string",
      "description": "The site’s industry category, if one fits: professional-services (consulting, accounting, audit, law), agencies (marketing, advertising, creative), ecommerce-retail (online shops, retail, wholesale), manufacturing. Map the user’s words, in any language, to one of these; if none fits (a bank, a hospital, a public body), leave it out."
    },
    "employees": {
      "type": "integer",
      "maximum": 10000000,
      "description": "Number of employees, e.g. 120.",
      "exclusiveMinimum": 0
    }
  }
}
review_ai_transformation_plan annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
find_practices — Find rated practices for adopting AI
Advertised by the server during the last successful anonymous check.
Advertised read-only

List practices for adopting AI that fit a company's size, rated by strength of evidence. Use it for 'Where should we start with AI?' or 'What should a 120-person manufacturer do first?'. Pass the number of employees or a size band, and optionally the theme, stage or priority. Returns the practices in one line each, or a menu by theme when there are many; fetch the ones you use with get_evidence for their studies, cases and links.

find_practices input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "size": {
      "type": "string",
      "maxLength": 500,
      "description": "Company size band: micro-small, medium, mid-market, enterprise (1–49, 50–249, 250–999, 1,000+ employees). Or pass employees instead."
    },
    "stage": {
      "enum": [
        "explore",
        "adopt",
        "redesign",
        "run"
      ],
      "type": "string",
      "description": "How far the company is: explore, adopt, redesign or run."
    },
    "theme": {
      "type": "string",
      "maxLength": 500,
      "description": "A theme key from start, e.g. governance-and-risk or people-and-skills."
    },
    "priority": {
      "enum": [
        "do first",
        "do next",
        "do later"
      ],
      "type": "string",
      "description": "Practices with this priority."
    },
    "employees": {
      "type": "integer",
      "maximum": 10000000,
      "description": "Number of employees, e.g. 120.",
      "exclusiveMinimum": 0
    }
  }
}
find_practices annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
find_company_cases — Find company cases of AI use
Advertised by the server during the last successful anonymous check.
Advertised read-only

List real companies that used AI and how it turned out: measured result, company-reported result, went wrong, or partly walked back. Use it for 'Who has done this?' or 'What went wrong for others?'. Filter by the kind of work AI was used for (task), outcome, theme, industry or company size; returns the cases in one line each, or a menu with counts when there are many. Fetch the ones you use with get_evidence for the story, who produced the figures and the public sources.

find_company_cases input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "size": {
      "type": "string",
      "maxLength": 500,
      "description": "Company size band: micro-small, medium, mid-market, enterprise (1–49, 50–249, 250–999, 1,000+ employees). Or pass employees instead."
    },
    "task": {
      "type": "string",
      "maxLength": 500,
      "description": "The kind of work AI was used for: a task key from start, e.g. customer-service-and-support."
    },
    "theme": {
      "type": "string",
      "maxLength": 500,
      "description": "A theme key from start, e.g. governance-and-risk or people-and-skills."
    },
    "outcome": {
      "enum": [
        "measured",
        "company-reported",
        "went-wrong",
        "walked-back"
      ],
      "type": "string",
      "description": "Cases with this outcome: measured, company-reported, went-wrong or walked-back."
    },
    "industry": {
      "enum": [
        "professional-services",
        "agencies",
        "ecommerce-retail",
        "manufacturing",
        "other"
      ],
      "type": "string",
      "description": "Cases in this industry: professional-services, agencies, ecommerce-retail, manufacturing, or other (none of the four, e.g. banks, airlines, public bodies). Practices apply to all industries."
    },
    "employees": {
      "type": "integer",
      "maximum": 10000000,
      "description": "Number of employees, e.g. 120.",
      "exclusiveMinimum": 0
    }
  }
}
find_company_cases annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
find_readiness_assessment — Find an AI readiness or literacy assessment
Advertised by the server during the last successful anonymous check.
Advertised read-only

List published questionnaires, tests and task maps to assess AI readiness, AI literacy, staff attitudes or which tasks suit AI, best tested first, optionally by kind or free to use. Fetch the ones that fit with get_evidence for how well each has been tested, who answers it, its length, licence and cost. For advice on what to do, use find_practices.

find_readiness_assessment input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "kind": {
      "type": "string",
      "maxLength": 500,
      "description": "The kind key from start, e.g. readiness-surveys or ai-knowledge-tests-and-self-ratings."
    },
    "free_only": {
      "type": "boolean",
      "description": "Only assessments that are free to use."
    }
  }
}
find_readiness_assessment annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
board_brief — Prepare a board brief on AI adoption
Advertised by the server during the last successful anonymous check.
Advertised read-only

Prepare a one-page board brief on a question about AI adoption, from rated evidence only. Returns the company cases by the kind of work AI was used for, the themes (with practice counts for the company’s size), the claim checks and figure groups, and how to write the brief: open the cases for the work in question and one to three themes, fetch eight to twelve records and write from them. Use it when someone needs a summary for a board, an owner or an investment committee. To review a written plan, use review_ai_transformation_plan.

board_brief input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "size": {
      "type": "string",
      "maxLength": 500,
      "description": "Company size band: micro-small, medium, mid-market, enterprise (1–49, 50–249, 250–999, 1,000+ employees). Or pass employees instead."
    },
    "industry": {
      "enum": [
        "professional-services",
        "agencies",
        "ecommerce-retail",
        "manufacturing"
      ],
      "type": "string",
      "description": "The site’s industry category, if one fits: professional-services (consulting, accounting, audit, law), agencies (marketing, advertising, creative), ecommerce-retail (online shops, retail, wholesale), manufacturing. Map the user’s words, in any language, to one of these; if none fits (a bank, a hospital, a public body), leave it out."
    },
    "employees": {
      "type": "integer",
      "maximum": 10000000,
      "description": "Number of employees, e.g. 120.",
      "exclusiveMinimum": 0
    }
  }
}
board_brief annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

1 advertised

due_diligence — AI transformation due diligence

Advertised by the server during the last successful anonymous check.

Run a due-diligence review of an AI business case, vendor proposal or transformation plan, step by step, using the ai-first.company tools for every evidence claim.

subject
The plan, proposal or business case to review, pasted as text, or a short description of it. (required)
company
The company: number of employees and industry, e.g. "120 people, manufacturing".

Resources

7 advertised

practices — Practices for adopting AI, rated by evidence

Advertised by the server during the last successful anonymous check.

Practices for adopting AI, rated by evidence, as published at https://www.ai-first.company/data/practices.json (CC BY 4.0).

practices URI
ai-first://practices

MIME type: application/json

cases — Company cases of AI use, with outcomes

Advertised by the server during the last successful anonymous check.

Company cases of AI use, with outcomes, as published at https://www.ai-first.company/data/cases.json (CC BY 4.0).

cases URI
ai-first://cases

MIME type: application/json

assessments — AI readiness assessments

Advertised by the server during the last successful anonymous check.

AI readiness assessments, as published at https://www.ai-first.company/data/assessments.json (CC BY 4.0).

assessments URI
ai-first://assessments

MIME type: application/json

studies — Studies of AI at work

Advertised by the server during the last successful anonymous check.

Studies of AI at work, as published at https://www.ai-first.company/data/studies.json (CC BY 4.0).

studies URI
ai-first://studies

MIME type: application/json

claim-checks — Checks of widely repeated AI figures

Advertised by the server during the last successful anonymous check.

Checks of widely repeated AI figures, as published at https://www.ai-first.company/data/claim-checks.json (CC BY 4.0).

claim-checks URI
ai-first://claim-checks

MIME type: application/json

figures — Payback figures with sources

Advertised by the server during the last successful anonymous check.

Payback figures with sources, as published at https://www.ai-first.company/data/figures.json (CC BY 4.0).

figures URI
ai-first://figures

MIME type: application/json

guide — Where to start: the map of the evidence, values and labels

Advertised by the server during the last successful anonymous check.

guide URI
ai-first://guide

MIME type: text/markdown

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
1649 ms
95th percentile latency
1649 ms

Maintenance history

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

  • · probe · passed · 1649 ms · metadata changed · 10 tool(s), 7 resource(s), 0 resource template(s), 1 prompt(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 ai-first-company-mcp https://mcp.ai-first.company/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 ai-first-company-mcp --url https://mcp.ai-first.company/mcp

Cursor

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

Cline

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

VS Code

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

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "ai-first-company-mcp": {
      "url": "https://mcp.ai-first.company/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": {
    "ai-first-company-mcp": {
      "serverUrl": "https://mcp.ai-first.company/mcp"
    }
  }
}

Let your agent find its tools

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

Connect Koskamo Explore workflows
See all 977

Do you run AI-first company MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing