Skip to content
Perq logo

Perq MCP server

Which MCP servers are Perq'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 2026-10-28

← Back to Perq

Whose server it is
  • Registry namesh.perq/perqverified in the MCP registry

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

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools8
  • Server calls itselfperq
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 373 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: find free AI API credits from vendors; check whether a credit offer is still live; compare cloud and LLM startup credits across providers.
  • Checked on 5 of the 7 days it takes to judge reliability.

Once connected

  • For "find free AI API credits from vendors", the likely first call is find_credits.
  • For "check whether a credit offer is still live", the likely first call is get_offer.
  • For "compare cloud and LLM startup credits across providers", the likely first call is find_credits.

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: 5, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring5 of the 7 daily checks it takes to print a share
  • Median first answer416 ms
  • Space in an agent's context≈ 1,597 tokensthe definitions of all its tools (8), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · find free AI API credits from vendors
  • can do · check whether a credit offer is still live
  • can do · compare cloud and LLM startup credits across providers

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

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 offers8 tools · read 2026-10-28
  • find_credits

    Answer "what free credits / free tier / startup program can I get for X". Ranked, verified offers matching a need such as "free speech to text credits", "GPU for a bootstrapped startup" or "student LLM API credits". Each result has…

  • trending

    Offers people are actually claiming (clicks on the claim link, one per visitor per day) or voting "worked for me", over the last 7 days or all time. Counts are real and never seeded; when nothing has been claimed yet the list is empty and…

  • get_offer

    Full record for one Perq offer by id (e.g. "deepgram-200-credit"), including source quote, last_verified, recorded changes and packs that contain it.

  • list_packs

    Curated bundles of offers (e.g. AI startup launch pack, LLM API free tier pack, voice AI pack) with each pack's headline and up-to total where one is computed.

  • get_pack

    One curated pack by slug with every offer in it and how its up-to total was computed (which offers counted and why others did not).

  • recently_changed

    Offers added, updated (value, eligibility, claim steps) or closed in the last N days (dates in America/New_York).

  • subscribe

    Get newly verified offers before they are public on https://perq.sh (about 24h early), plus closures and changes. Give either email (a person: we send a confirmation link, then a digest only on days with something new) or webhook_url (an…

  • early_offers

    Offers that are verified but not public yet (embargoed, each with public_after), plus new, changed and closed offer events from the last 30 days, filtered by the subscription topics. Needs the private feed token from subscribe (webhook)…

How to connect

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

{
  "mcpServers": {
    "perq": {
      "type": "http",
      "url": "https://perq.sh/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http perq https://perq.sh/mcp

Add to CursorAdd to VS Code

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

OpenAPI spec

10 paths, read 2026-10-28. Open the spec ↗

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.