MCP.Market

Perq MCP server

online · 100% uptime
by perq.sh·sh.perq/perq·v1.0.1
No reviews yet

Verified free AI credits, free tiers and startup programs, each with source link and verified date.

A91/100grade A
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
A91/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed Perq yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Perq tools (8)

write = sends, deletes, buys or posts
  • early_offersFree

    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) or from the email confirmation page.

  • find_creditsFree

    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 credit_value, eligibility, how_to_claim, claim_url, source_url, source_snippet (verbatim vendor quote), last_verified, value_usd (explicit one-time USD amount or null), audience, and live claims / claims_7d / votes counts (real visitors, never padded; null if unavailable). filters.sort orders by relevance (default), popular (most claimed this week), votes, newest, verified (most recently re-checked), value (largest stated USD credit) or az. need may be empty when you only filter/sort. Closed offers are excluded unless filters.status is "all"/"closed" or include_closed is true. claim_redirect_url sends the user to the vendor and counts the claim anonymously; claim_url is the direct vendor link.

  • get_offerFree

    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.

  • get_packFree

    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).

  • list_packsFree

    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.

  • recently_changedFree

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

  • subscribeFree

    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 agent: https only, public hosts only; each new offer is POSTed as JSON signed with HMAC-SHA256). A webhook signup returns the signing secret once, a private feed token for early_offers, and the result of a signed verification ping. Only subscribe an address or URL the user asked you to.

  • trendingFree

    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 says so.

Public scan report

scanner v0.1.10 · 2026-10-26 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 826ms20/20
  • Tool poisoning8 tool descriptions checked15/15
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityendpoint served from the registry-verified namespace domain8/10
Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Perq compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 85% of 48,255 servers
Tools
8
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
411 ms
faster than 36% of 30,031 servers

What its tools let an agent do: 8 read

Install Perq in Claude Code, Cursor or VS Code

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

What the publisher says

From the Perq repository's README, as published. We do not edit it. Read it on GitHub

Perq skill

An agent skill (plus a remote MCP server) that answers "what free AI credits can I get for X?" with verified offers from Perq: free tiers, signup credits, startup programs, student and research perks, and perk marketplaces for AI APIs, models, GPUs and dev tools.

Every offer comes from the vendor's own page and includes the source URL, a verbatim quote from that page, and a last-verified timestamp. The skill tells the agent to show the source link and date with every offer and never to invent offers or amounts.

It works with Claude Code, Codex, Cursor, Hermes Agent, and any agent that reads SKILL.md files (agentskills.io format).

  • Website: https://perq.sh
  • Agent docs: https://perq.sh/agents
  • Search API: GET https://perq.sh/api/search?q=
  • MCP server: https://perq.sh/mcp (Streamable HTTP, no auth, read-only)
  • llms.txt: https://perq.sh/llms.txt

The skill is one file: skills/perq/SKILL.md. The repo also has:

  • .claude-plugin/plugin.json and marketplace.json: Claude Code plugin (skill + MCP server)
  • .mcp.json: the remote MCP server config for clients that read it
  • gemini-extension.json: Gemini CLI extension (MCP server + skill as context)
  • server.json: the official MCP Registry entry (sh.perq/perq)

Install

Any agent (skills.sh)

npx skills add f-o-x11/perq-skill

Add -g to install for all projects, or -a claude-code, -a codex, -a cursor, or -a hermes-agent to pick the agent.

Claude Code

As a plugin (installs the skill and the MCP server):

claude plugin marketplace add f-o-x11/perq-skill
claude plugin install perq@perq

MCP server only:

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

Or as a plain skill:

mkdir -p ~/.claude/skills/perq && curl -fsSL https://perq.sh/skill.md -o ~/.claude/skills/perq/SKILL.md

Codex

npx skills add f-o-x11/perq-skill -a codex -g

Cursor

npx skills add f-o-x11/perq-skill -a cursor

Or add the MCP server to ~/.cursor/mcp.json:

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

Gemini CLI

gemini extensions install https://github.com/f-o-x11/perq-skill

Hermes Agent

hermes skills install f-o-x11/perq-skill/skills/perq

What it does

Ask your agent "what free credits can I get for speech-to-text?" The agent runs:

curl -sS -G "https://perq.sh/api/search" --data-urlencode "q=free speech to text credits" -d limit=5 -d ref=skill

and answers with each offer's value, eligibility, claim link, source link and last-verified date. Filters: category, type, student=true, noapplication=true, includeclosed=true, limit.

MCP tools: findcredits(need, filters), getoffer(id), listpacks(), getpack(slug), recently_changed(days).

ref=skill tells Perq that a search came from this skill. It does not change the results.

License

MIT. Copyright (c) 2026 Avatar 8 LLC.

Perq is operated by Avatar 8 LLC. Contact: ops@avatar33.com. No paid ranking: vendors cannot pay to be listed or to move up.

Nothing above is checked by us. What we check is on the safety report.

Perq: common questions

Is Perq MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the Perq safety report
How do I install Perq?
It runs remotely at perq.sh. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Perq need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Perq maintained?
The last commit was 9 days ago (2026-10-26). The latest release is v1.0.1.
Is Perq up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Perq compare with other MCP servers?
safety score 91/100 (higher than 85% of 48,255 servers); tools 8 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.