Dataconto MCP server

• Registry namecom.dataconto/buyersverified in the MCP registry

The registry name sits under dataconto.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-28
• Tools9
• Server calls itselfdataconto
• Server version1.2.0
• Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 152 ms.

• Its tools do every use case we checked: check which AI buyers would license company records; estimate what private code repositories could earn.
• Checked on 6 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
• What an agent can do with it2 of 2 use cases
• Answeredmeasuring6 of the 7 daily checks it takes to print a share
• Median first answer166 ms
• Space in an agent's context≈ 3,534 tokensthe definitions of all its tools (9), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results0 of 9 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• list_buyers

  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…

• get_buyer

  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_market_facts

  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_tool_terms

  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…

• fit_check

  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…

• estimate

  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…

• code_value

  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…

• deletion_clock

  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)…

• rights_check

  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…