Koskamo

Dataconto MCP

An official read-only MCP server that allows AI agents to query Dataconto's database of buyers who pay for company records and private code. It provides tools to list buyers, retrieve market facts, check tool terms, and run fit checks, estimators, and rights assessments for data licensing opportunities.

Visit Dataconto

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.

Dataconto MCP logo, by DatacontoVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Dataconto
MCP endpoint (Streamable HTTP)
https://dataconto.com/mcp
Vendor documentation

What you can do with it

  • List buyers paying for company records or code
  • Check if a company's data fits buyer criteria
  • Estimate potential payout for data assets
  • Verify data licensing rights and deletion clocks

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: com.dataconto/buyers@1.0.0Project website

Protocol and capabilities

Server
dataconto 1.2.0
MCP protocol
2025-06-18
Tools
9 advertised
Resources
4 advertised
Resource templates
0 advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  },
  "resources": {
    "listChanged": false
  }
}

Server-provided instructions

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

Dataconto shows owners who would pay for what they have: AI companies and data buyers that license a company's business records (email, chat, support tickets, documents, CRM and databases), private source code and datasets. Many take records from companies that are winding down or have closed. Each program comes with the terms the buyer publishes for owners (who qualifies, what it takes, payout ranges and rates, when the owner is paid), quoted from the buyer's own page with the date it was read. Use list_buyers to find programs that fit an owner, get_buyer for one program and its facts, and get_market_facts for dated figures across programs. The fit check at https://dataconto.com/company (records) or https://dataconto.com/code (code) matches an owner against published terms. Dataconto doesn't hold, broker or price the data. A second dataset, get_tool_terms, answers what a business tool's own terms say about the customer's data (Slack, Microsoft 365, Google Workspace, Salesforce, Notion and others): who owns it, whether the vendor trains AI on it, what can be exported on which plan, and what happens after cancellation, each a dated quote from the vendor's page. Five tools run the site's checks for one owner: fit_check (which buyers' published criteria the owner's answers meet), estimate (three buyers' own public payout estimators side by side, and where an offer the owner received sits against them), code_value (private code priced at a buyer's published per-token rates), deletion_clock (the last day to export from each tool after the account ends) and rights_check (whether the records are ready to license, and what to settle before signing). Figures are the buyers' and vendors' own, each with the date it was checked; none is an offer. The data is CC BY 4.0.

Tools

9 advertised

list_buyers — List who buys company records and code
Advertised by the server during the last successful anonymous check.
Advertised read-only

Programs that pay owners for company records (email, chat, tickets, docs, CRM, databases) or private code, including from closed or winding-down companies. Returns each program's summary, who qualifies, published payout range or rates, countries and its Dataconto page. Programs listed on Dataconto's buyer pages come first.

list_buyers input schema
{
  "type": "object",
  "properties": {
    "kind": {
      "enum": [
        "pays_owner",
        "marketplace",
        "invite_only"
      ],
      "type": "string",
      "description": "pays_owner = the program pays the owner itself; marketplace = it places the data with buyers; invite_only = no open intake."
    },
    "side": {
      "enum": [
        "company",
        "code"
      ],
      "type": "string",
      "description": "company = business records, code = private source code."
    },
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "Results to return, default 20."
    },
    "listed": {
      "type": "boolean",
      "description": "true = only programs on Dataconto's buyer pages and fit check."
    },
    "status": {
      "enum": [
        "open",
        "invite",
        "paused",
        "closed"
      ],
      "type": "string",
      "description": "Intake status."
    },
    "country": {
      "type": "string",
      "description": "Two-letter ISO 3166 code of the owner's country, e.g. US, GB, DE. Programs with no country limit are included."
    },
    "min_payout": {
      "type": "integer",
      "minimum": 0,
      "description": "Only programs whose published payout reaches at least this many US dollars."
    }
  },
  "additionalProperties": false
}
list_buyers annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_buyer — Get one buyer program
Advertised by the server during the last successful anonymous check.
Advertised read-only

One program with its current facts: what it takes, who qualifies, payout, fees, exclusivity, payment timing and process, each quoted from the buyer's page with the date read.

get_buyer input schema
{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Program id from list_buyers, e.g. \"scale-data-partnerships\". A company name also works."
    }
  },
  "additionalProperties": false
}
get_buyer annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_market_facts — Dated market facts on data and code buyers
Advertised by the server during the last successful anonymous check.
Advertised read-only

Dated, sourced facts across programs: payout ranges, per-token rates, payout caps, platform fees, payment timing, eligibility. History is kept when a term changes (current=false rows). Press-only figures are flagged with source_type press.

get_market_facts input schema
{
  "type": "object",
  "properties": {
    "field": {
      "enum": [
        "payout_range",
        "payout_rate",
        "payout_cap",
        "payout_total",
        "platform_fee",
        "payment_timing",
        "exclusivity",
        "eligibility",
        "buys",
        "process",
        "deal",
        "ownership"
      ],
      "type": "string",
      "description": "Kind of fact."
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Results to return, default 30."
    },
    "since": {
      "type": "string",
      "description": "Observed on or after this date, YYYY-MM-DD."
    },
    "current": {
      "type": "boolean",
      "description": "true = only terms in force; false = only superseded ones."
    },
    "program": {
      "type": "string",
      "description": "Program id from list_buyers."
    },
    "source_type": {
      "enum": [
        "primary",
        "press",
        "register"
      ],
      "type": "string",
      "description": "primary = quoted from the buyer's own page."
    }
  },
  "additionalProperties": false
}
get_market_facts annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_tool_terms — What a business tool's terms say about customer data
Advertised by the server during the last successful anonymous check.
Advertised read-only

For business tools companies keep records in (chat, email, tickets, docs, CRM, call recordings, code hosts): who owns the customer's data, whether the vendor trains AI on it (generative and other models, by plan), whether it keeps aggregated use, what can be exported on which plan and by whom, how much history the plan keeps, and how long data stays after cancellation. Each answer is quoted word for word from the vendor's own terms, AI page, data processing addendum or help article, with the date read. "The terms don't say" means every contract was read and none answers; "Not read yet" means a document is still unread. Answers marked inferred are a reading of the text, not its words. Not legal advice.

get_tool_terms input schema
{
  "type": "object",
  "properties": {
    "plan": {
      "type": "string",
      "description": "A plan name as the vendor spells it, e.g. \"Free\", \"Enterprise\"."
    },
    "tool": {
      "type": "string",
      "description": "Tool id, e.g. \"slack\", \"microsoft-365\", \"google-workspace\", \"salesforce\", \"notion\". Omit to list every tool."
    },
    "facts": {
      "type": "boolean",
      "description": "false = headline answers only, no quoted facts. Default true."
    },
    "field": {
      "enum": [
        "ownership",
        "ai_training",
        "aggregate_use",
        "export",
        "retention",
        "after_cancel"
      ],
      "type": "string",
      "description": "One question: ownership, ai_training, aggregate_use, export, retention or after_cancel."
    },
    "limit": {
      "type": "integer",
      "maximum": 20,
      "minimum": 1,
      "description": "Tools to return, default 20."
    },
    "answer": {
      "enum": [
        "customer",
        "vendor",
        "shared",
        "not_stated",
        "no",
        "opt_in",
        "opt_out",
        "yes",
        "reserved",
        "not_reserved",
        "all",
        "partial",
        "none",
        "days",
        "export",
        "no_export"
      ],
      "type": "string",
      "description": "Keep tools whose headline answer has this token, e.g. opt_out with field=ai_training."
    },
    "record_type": {
      "type": "string",
      "description": "Kind of record: slack-and-teams, email, support-tickets, jira-and-linear, crm, call-recordings, documents-and-sops."
    }
  },
  "additionalProperties": false
}
get_tool_terms annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
fit_check — Check which buyers fit a company's records or code
Advertised by the server during the last successful anonymous check.
Advertised read-only

Runs Dataconto's fit check: each listed buyer's published criteria against the owner's answers. Returns, per buyer program, a verdict (strong = every criterion met, possible = none failed but some unknown, none = a criterion failed), each criterion as met, failed or unknown, the reasons for a miss, the buyer's published figure with the date checked and its Dataconto page. Unanswered questions count as unknown; `missing` lists the ones worth asking.

fit_check input schema
{
  "type": "object",
  "required": [
    "side"
  ],
  "properties": {
    "side": {
      "enum": [
        "company",
        "code"
      ],
      "type": "string",
      "description": "company = business records, code = private source code."
    },
    "answers": {
      "type": "object",
      "properties": {
        "owner": {
          "enum": [
            "me",
            "company",
            "client",
            "unsure"
          ],
          "type": "string",
          "description": "Code side."
        },
        "repos": {
          "type": "integer",
          "maximum": 10000,
          "minimum": 1,
          "description": "Code side. Number of repositories."
        },
        "staff": {
          "type": "integer",
          "maximum": 100000,
          "minimum": 1,
          "description": "Company side. People now, or at the peak if closing or closed."
        },
        "years": {
          "type": "integer",
          "maximum": 100,
          "minimum": 0,
          "description": "Company side. Years of records still held."
        },
        "access": {
          "enum": [
            "yes",
            "some",
            "exports",
            "none"
          ],
          "type": "string",
          "description": "Company side, closing or closed only. Can someone still sign in."
        },
        "origin": {
          "enum": [
            "original",
            "fork",
            "mix"
          ],
          "type": "string",
          "description": "Code side."
        },
        "public": {
          "enum": [
            "never",
            "some",
            "unsure"
          ],
          "type": "string",
          "description": "Code side. Was any of it ever public."
        },
        "signer": {
          "enum": [
            "founder",
            "officeholder",
            "assignee",
            "unsure"
          ],
          "type": "string",
          "description": "Company side, closing or closed only. Who can sign now."
        },
        "status": {
          "enum": [
            "operating",
            "closing",
            "closed"
          ],
          "type": "string",
          "description": "Company side."
        },
        "country": {
          "enum": [
            "us",
            "uk",
            "ca",
            "au",
            "eu4",
            "eu",
            "in",
            "sg",
            "other"
          ],
          "type": "string",
          "description": "Company side. Headquarters: us, uk, ca, au, eu4 (Ireland, Netherlands, Germany or France), eu (another EU country), in, sg, other."
        },
        "english": {
          "enum": [
            "most",
            "some",
            "little"
          ],
          "type": "string",
          "description": "Company side. How much of the records is in English."
        },
        "history": {
          "enum": [
            "full",
            "partial",
            "none"
          ],
          "type": "string",
          "description": "Code side. Git history."
        },
        "systems": {
          "type": "array",
          "items": {
            "enum": [
              "slackteams",
              "chat",
              "email",
              "calls",
              "tickets",
              "support",
              "docs",
              "databases",
              "crm",
              "accounting",
              "code"
            ],
            "type": "string"
          },
          "description": "Company side. slackteams = Slack or Microsoft Teams; tickets = Jira, Linear, Asana; support = Zendesk, Intercom."
        },
        "contents": {
          "type": "array",
          "items": {
            "enum": [
              "secrets",
              "customerdata",
              "thirdparty",
              "contractor"
            ],
            "type": "string"
          },
          "description": "Code side."
        },
        "industry": {
          "enum": [
            "legal",
            "finance",
            "nonprofit",
            "other"
          ],
          "type": "string",
          "description": "Company side. finance covers accounting, finance and medical."
        },
        "sensitive": {
          "type": "array",
          "items": {
            "enum": [
              "pii",
              "health",
              "card",
              "contractor"
            ],
            "type": "string"
          },
          "description": "Company side."
        }
      },
      "description": "Answer what you know; leave the rest out.",
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}
fit_check annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
estimate — Run three buyers' published payout estimators
Advertised by the server during the last successful anonymous check.
Advertised read-only

What micro1's, Telegraph's and Grepped's own public estimators give for a company's records, from team size, years in business and headquarters (revenue optional, Grepped only). Each range is the buyer's formula, checked against its live page on the date given; none is an offer and Dataconto adds no figure of its own. Pass offer_usd (and offer_from) to place an offer the owner received against each range and the offering buyer's published range. Also returns the other listed buyers these answers don't rule out.

estimate input schema
{
  "type": "object",
  "required": [
    "staff",
    "years"
  ],
  "properties": {
    "staff": {
      "type": "integer",
      "maximum": 100000,
      "minimum": 1,
      "description": "People now, or at the peak."
    },
    "years": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Years in business."
    },
    "status": {
      "enum": [
        "operating",
        "closing",
        "closed"
      ],
      "type": "string",
      "description": "Default operating. micro1's estimator covers running companies only."
    },
    "country": {
      "enum": [
        "us",
        "uk",
        "ca",
        "au",
        "eu4",
        "eu",
        "in",
        "sg",
        "other"
      ],
      "type": "string",
      "description": "Headquarters: us, uk, ca, au, eu4 (Ireland, Netherlands, Germany or France), eu (another EU country), in, sg, other. Default us."
    },
    "revenue": {
      "enum": [
        "pre",
        "0-1m",
        "1-10m",
        "10-50m",
        "50-200m",
        "200m+",
        "undisclosed"
      ],
      "type": "string",
      "description": "Annual revenue band, Grepped only. Default undisclosed."
    },
    "offer_usd": {
      "type": "integer",
      "maximum": 10000000000,
      "minimum": 1,
      "description": "An offer the owner received, in US dollars."
    },
    "offer_from": {
      "enum": [
        "micro1",
        "mode",
        "scale",
        "turing",
        "telegraph",
        "handshake",
        "grepped",
        "miro-advisory",
        "license-my-data",
        "maryah",
        "other"
      ],
      "type": "string",
      "description": "Who made the offer."
    }
  },
  "additionalProperties": false
}
estimate annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
code_value — Price private code at a buyer's published per-token rates
Advertised by the server during the last successful anonymous check.
Advertised read-only

Counts code the way pre.dev's public script does (code files in full, text files up to 10x the code, minified and bundle-named files skipped, 4 bytes per token) and prices it at Pangea's published non-exclusive list rates per million tokens of source and of git history. Give files (path and size in bytes, e.g. from `git ls-tree -r -l HEAD`), or code_bytes and text_bytes, or source_tokens. History is optional. A list price, not an offer.

code_value input schema
{
  "type": "object",
  "properties": {
    "files": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "path",
          "size"
        ],
        "properties": {
          "path": {
            "type": "string",
            "maxLength": 500
          },
          "size": {
            "type": "integer",
            "maximum": 100000000000,
            "minimum": 0
          }
        },
        "additionalProperties": false
      },
      "maxItems": 5000,
      "description": "Files at HEAD, paths relative to the repo root. Skip rules (node_modules, vendor, build output) are applied here."
    },
    "code_bytes": {
      "type": "integer",
      "maximum": 10000000000000,
      "minimum": 0,
      "description": "Bytes of code files, if you summed them yourself."
    },
    "text_bytes": {
      "type": "integer",
      "maximum": 10000000000000,
      "minimum": 0,
      "description": "Bytes of text files (Markdown, JSON, YAML, HTML)."
    },
    "source_tokens": {
      "type": "integer",
      "maximum": 10000000000000,
      "minimum": 0,
      "description": "Source tokens, if already counted."
    },
    "history_tokens": {
      "type": "integer",
      "maximum": 10000000000000,
      "minimum": 0,
      "description": "Git history tokens, if counted."
    }
  },
  "additionalProperties": false
}
code_value annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
deletion_clock — Last day to export from each business tool
Advertised by the server during the last successful anonymous check.
Advertised read-only

For a company canceling its tools or closing: the last day to export from each tool once the account ends, by plan, from what each vendor's own terms say happens after cancellation (export window in days, kept with no export, or nothing). Each row quotes the vendor's words with the date read. With no plan given, the plan with the shortest window is used and flagged. Tool ids as in get_tool_terms.

deletion_clock input schema
{
  "type": "object",
  "properties": {
    "ends": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "Day the accounts end, YYYY-MM-DD, between 2000 and 2100. Default today (UTC)."
    },
    "plans": {
      "type": "object",
      "description": "Plan per tool as the vendor spells it, e.g. {\"slack\": \"Pro\"}. Keys are tool ids.",
      "additionalProperties": {
        "type": "string",
        "maxLength": 60
      }
    },
    "tools": {
      "type": "array",
      "items": {
        "enum": [
          "slack",
          "github",
          "intercom",
          "atlassian",
          "sentry",
          "vercel",
          "hubspot",
          "zendesk",
          "google-workspace",
          "notion",
          "microsoft-teams",
          "salesforce",
          "microsoft-365",
          "linear",
          "asana",
          "zoom",
          "gong",
          "freshdesk",
          "discord",
          "dropbox",
          "figma",
          "quickbooks",
          "xero"
        ],
        "type": "string"
      },
      "maxItems": 40,
      "description": "Tool ids, e.g. [\"slack\", \"google-workspace\", \"hubspot\"]. Omit for every tool."
    }
  },
  "additionalProperties": false
}
deletion_clock annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
rights_check — Check whether a company's records are ready to license
Advertised by the server during the last successful anonymous check.
Advertised read-only

Dataconto's rights check: from who can sign, customer contracts, personal data, staff and contractor IP and the tools the company uses, a verdict (ready = nothing in the way, work = steps to finish before signing, not_yet = nobody known who can sign for a closing or closed company) and the steps, each with its level (block, work, note, ok) and the Dataconto page that holds its source. Unanswered questions count as not sure and are listed in `missing`. With tools, also returns what each tool's terms say on ownership, export and AI training, each quote dated. Sums up published sources; not legal advice. Tool ids as in get_tool_terms.

rights_check input schema
{
  "type": "object",
  "required": [
    "status"
  ],
  "properties": {
    "ip": {
      "enum": [
        "all",
        "gaps",
        "unsure",
        "na"
      ],
      "type": "string",
      "description": "Whether staff and contractor agreements assign their work to the company. gaps = not all of them; na = no documents or code in scope."
    },
    "tools": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 40,
      "description": "Tool ids the company uses, e.g. [\"slack\", \"notion\"]."
    },
    "signer": {
      "enum": [
        "officer",
        "officeholder",
        "unsure"
      ],
      "type": "string",
      "description": "Who can sign for the company now. officer = a director or officer; officeholder = an administrator, liquidator or trustee."
    },
    "status": {
      "enum": [
        "operating",
        "closing",
        "closed"
      ],
      "type": "string",
      "description": "operating, closing (winding down) or closed."
    },
    "personal": {
      "enum": [
        "none",
        "some",
        "lots",
        "regulated"
      ],
      "type": "string",
      "description": "Personal data in the records. regulated = health or financial records."
    },
    "contracts": {
      "enum": [
        "some",
        "none",
        "unsure"
      ],
      "type": "string",
      "description": "Whether any customer contracts limit what the company can do with their data."
    }
  },
  "additionalProperties": false
}
rights_check annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

4 advertised

fit-check — Fit check cards

Advertised by the server during the last successful anonymous check.

One card per listed program: strong fit, possible fit or near miss with the reason, the program's published figure and the date it was checked.

fit-check URI
ui://widget/dataconto-fit-check-v1.html

MIME type: text/html;profile=mcp-app

estimate — Payout estimators side by side

Advertised by the server during the last successful anonymous check.

micro1's, Telegraph's and Grepped's own estimator ranges side by side, each with the date it was checked, and where an offer sits against them.

estimate URI
ui://widget/dataconto-estimate-v1.html

MIME type: text/html;profile=mcp-app

deletion-clock — Export deadlines

Advertised by the server during the last successful anonymous check.

The last day to export from each business tool, soonest first, with the vendor's words and the date they were read.

deletion-clock URI
ui://widget/dataconto-deletion-clock-v1.html

MIME type: text/html;profile=mcp-app

code-value — Code list price

Advertised by the server during the last successful anonymous check.

Private code priced at a program's published per-token rates, with the rates and the date they were checked.

code-value URI
ui://widget/dataconto-code-value-v1.html

MIME type: text/html;profile=mcp-app

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
427 ms
95th percentile latency
427 ms

Maintenance history

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

  • · probe · passed · 427 ms · metadata changed · 9 tool(s), 4 resource(s), 0 resource template(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 dataconto-mcp https://dataconto.com/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 dataconto-mcp --url https://dataconto.com/mcp

Cursor

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

Cline

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

VS Code

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

Let your agent find its tools

Find servers like Dataconto 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 4,071

Do you run Dataconto 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