Skip to content

Thruact MCP server

Which servers in the official MCP registry are Thruact's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-25

← Back to Thruact

Whose server it is
  • Registry namecom.thruact/thruactverified in the MCP registry

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

When we asked itchecked 2026-10-25
  • Stateanswerschecked 2026-10-25
  • Tools7
  • Server calls itselfthruact
  • Server version0.2.0
  • Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 168 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 5 of 7 tools: check arguments before calling.

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.

Measured dailydaily checks: 2, the first on 2026-10-25
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer402 ms
  • Space in an agent's context≈ 751 tokensthe definitions of all its tools (7), which an agent carries on every turn
  • Tool definitionsC · 71 of 100
  • Typed results0 of 7 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 5 of 7
  • Not saying whether it only reads or can destroy: 7 of 7

Worth a look

None of the five warning signs in these definitions.

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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 →

Tools it offers7 tools · read 2026-10-25
  • thruact_discover

    Find capabilities for a job, with prices and measured reliability. Search first, execute second.

  • thruact_act

    Run a capability. Routes across providers and fails over automatically on provider faults. The reply's `route` says which providers were considered, what each scored, and why any were not used — including ones dropped for a missing…

  • thruact_compare

    Ask every provider behind a capability the same question at once and report where their answers differ. Use it when the answer matters enough to want it corroborated. Costs more than act: every provider called is paid.

  • thruact_call

    Run one specific tool by id. No failover.

  • thruact_wallet

    Prepaid balance and recent charges.

  • thruact_iq

    Measured reliability per tool over the last 7 days.

  • thruact_proxy

    Send an authenticated request to a third-party vendor the workspace has connected. The stored API key is injected server-side — you never see it. Give the vendor id from the directory (e.g. openai, sendgrid), an HTTP method, and a path on…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "thruact": {
      "type": "http",
      "url": "https://thruact.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http thruact https://thruact.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://thruact.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.