Skip to content

Perq MCP server

sh.perq/perqperq.shstreamable-httpv1.0.1Scanned

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

8 tools: 4 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 4 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

4 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Perq MCP server can do

The Perq MCP server is published by perq.sh, a domain the MCP Registry verified. It has 8 tools. It can create or change data (4 tools: trending, recently_changed, subscribe and early_offers), but cannot delete data. 4 tools only read.

1 tool brings in text other people can write (subscribe); 1 tool can send data out of your system (subscribe).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 18, 2026, version 1.0.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

8 tools

Changes things 4Claude Code: ask
  • early_offersOffers 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 topic…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • recently_changedOffers added, updated (value, eligibility, claim steps) or closed in the last N days (dates in America/New_York).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Offers added, updated (value, eligibility, claim steps) or closed in the last N days (dates in America/New_York).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • subscribeGet newly verified offers before they are public on https://perq.sh (about 24h early), plus closures and changes.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "subscribe" says "subscribe": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 4Show 4 read-only tools
  • find_creditsAnswer "what free credits / free tier / startup program can I get for X".No findings

    Why it is in this group

    • The name "find_credits" says "find": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_offerFull record for one Perq offer by id (e.g.No findings

    Why it is in this group

    • The name "get_offer" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_packOne 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).No findings

    Why it is in this group

    • The name "get_pack" says "get": a word for reading.
    Description, as the server wrote it
    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).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_packsCurated bundles of offers (e.g.No findings

    Why it is in this group

    • The name "list_packs" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:18 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://perq.sh/mcp: tools/list returned 8 tools to an anonymous client, including trending (write), recently_changed (write), subscribe (write), early_offers (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools1 added, 1 changed.+1 added~1 changedView diff

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__perq__find_credits",
      "mcp__perq__get_offer",
      "mcp__perq__list_packs",
      "mcp__perq__get_pack"
    ],
    "ask": [
      "mcp__perq__trending",
      "mcp__perq__recently_changed",
      "mcp__perq__subscribe",
      "mcp__perq__early_offers"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as perq. Review it before you use it.

Capability tags behind 1 rule
  • mcp__perq__subscribe untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/sh.perq/perq/verify?hash=dde5b0ed28db0858cbfc3fd3e827b46d8d1b10bb763c25b8107c408681a304ae" | jq -e '.changed == false'

Pinned hash dde5b0ed28db, from Nov 18, 2026, 07:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/sh.perq/perq/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for sh.perq/perq
[![Anlyon Radar](https://radar.anlyon.com/badge/sh.perq/perq.svg)](https://radar.anlyon.com/servers/sh.perq/perq)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:54 UTC.

Perq MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Perq MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Perq MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Perq MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Perq MCP server have?

8 tools: 4 write, 4 read. trending, recently_changed, subscribe, early_offers, find_credits, get_offer, list_packs and get_pack.

Does the Perq MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Perq MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): subscribe.

Has the Perq MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 4, 2026. Every change is on this page and in its Atom feed.