Skip to content
Freemoney logo

Freemoney MCP server

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

read 2026-11-04

← Back to Freemoney

Whose server it is
  • Registry namecomputer.freemoney/creditsverified in the MCP registry

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

When we asked itchecked 2026-11-04
  • Stateanswerschecked 2026-11-04
  • Tools13
  • Server calls itselffreemoney
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-11-04 the server answered initialize and tools/list without a sign-in. First answer in 246 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 1 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 9 of 13 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: 1, the first on 2026-11-04
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer253 ms
  • Space in an agent's context≈ 2,363 tokensthe definitions of all its tools (13), which an agent carries on every turn
  • Tool definitionsB · 88 of 100
  • Typed results13 of 13 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 9 of 13

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 (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 →

Tools it offers13 tools · read 2026-11-04
  • search_credits

    Find free credits, free tiers, trials and startup, student or open-source programs from AI, GPU, cloud, database and developer-tool providers. Results come with who can get each one, what it needs and links.

  • credits_for_stack

    For a codebase: given the services it uses, list the free credits and programs each one's provider offers. Read package.json, requirements.txt, pyproject.toml, go.mod, Dockerfiles, Terraform and .env.example first and pass every external…

  • get_credit_program

    One program in full: the offer, who qualifies, every requirement, how long it lasts and its links.

  • search

    search_credits in the shape ChatGPT's deep research and company knowledge use: ids, titles and links. Pass an id to fetch. Other apps: use search_credits, which has eligibility and no-card filters.

  • fetch

    get_credit_program in the shape ChatGPT's deep research and company knowledge use.

  • search_offers

    Find AI/cloud credit programs and reviewed public promo codes. Use a provider name or keywords. Country is an ISO two-letter code; audiences supplement offers for anyone. Results include source, freshness, restrictions and community…

  • get_offer

    Read a specific offer's source, eligibility gates, public code if known, and community reports.

  • build_credit_stack

    Build a candidate bundle across providers matching the user's country and audiences. Eligibility still needs checking. Offers from one provider may overlap; totals and stacking are not guaranteed. Missing providers can be queued with…

  • request_promotion

    Queue a private request for a provider or missing promotion. Requires authentication remotely. Reuse request_key for retries of the same request. Do not include passwords, API keys or personal data. A catalog match does not mean the…

  • get_request_status

    Read your own queued request and any candidate matches. Requires the same caller identity.

  • claim_offer

    Get a reviewed public code when available, official redemption steps, and a private feedback receipt. This does not redeem, create an account, submit an application, or guarantee credits. Reuse request_key on retries. After the user…

  • report_promotion_result

    Report the user's actual redemption outcome for their claim receipt. One latest report per caller and offer revision counts. Community reports do not establish vendor-verified validity.

  • submit_promotion_code

    Submit a publicly shareable promo code and its source for operator review. Never submit an API key, account-specific voucher, or secret. Submissions remain private and cannot become a public code or verified offer merely by receiving…

How to connect

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

{
  "mcpServers": {
    "credits": {
      "type": "http",
      "url": "https://freemoney.computer/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http freemoney https://freemoney.computer/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://freemoney.computer/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.