Skip to content

Redeal MCP server

dev.redeal/redealredeal.devstreamable-httpv0.7.0Scanned

Neutral fairness computation for agents: fair division, verifiable random, Shapley shares.

12 tools: 6 change things and 6 only read.

Tools: 0 delete, 0 irreversible, 6 write, 6 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • 4 findings

Tools listed without sign-in. Remote posture

With Anlyon

6 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 Redeal MCP server can do

The Redeal MCP server is published by redeal.dev, a domain the MCP Registry verified. It has 12 tools. It can create or change data (6 tools: commit_input, compute_commitment_tool, create_deal, create_key and 2 more), but cannot delete data. 6 tools only read.

1 tool brings in text other people can write (get_entropy).

The fixed checks matched 4 findings (credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 11, 2026, version 0.7.0.

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.

12 tools

Changes things 6Claude Code: ask
  • commit_inputCommit your sealed input as a hash (sealed mode).No findings

    Why it is in this group

    • The name "commit_input" says "commit": a word for a change.
    Description, as the server wrote it
    Commit your sealed input as a hash (sealed mode). Nobody — including redeal — can see your input until all parties have committed. After the last commitment the deal opens for reveals immediately.
  • compute_commitment_toolCompute a commitment string for (input, salt): sha256(JCS(input) ++ salt_bytes), prefixed 'sha256:'.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.
    Description, as the server wrote it
    Compute a commitment string for (input, salt): sha256(JCS(input) ++ salt_bytes), prefixed 'sha256:'. Convenience only — the rule is public and you can compute it yourself.
  • create_dealCreate a fairness deal.No findings

    Why it is in this group

    • The name "create_deal" says "create": a word for a change.
    Description, as the server wrote it
    Create a fairness deal. You are party 0 (initiator). Returns a deal id and one invite token per party — give each counterparty their own token. Sealed mode: everyone commits a hash, then reveals; certificate is issued automatically when the deal computes or goes VOID.
  • create_keyGet a free redeal API key.No findings

    Why it is in this group

    • The name "create_key" says "create": a word for a change.
    Description, as the server wrote it
    Get a free redeal API key. No signup, no email — this is the entire onboarding. The key is shown once; store it. Use it as api_key in create_deal.
  • reveal_inputReveal your committed input.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.
    Description, as the server wrote it
    Reveal your committed input. It must hash to your earlier commitment. When the last party reveals, the deal computes and the fairness certificate is issued automatically — fetch it with get_certificate.
  • verify_certificateVerify a redeal certificate by id: signature check (current or published legacy key) + transparency-log inclusion check, reported per check.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...ion check, reported per check. Free, no credential required, always."

      What this check looks for
    Description, as the server wrote it
    Verify a redeal certificate by id: signature check (current or published legacy key) + transparency-log inclusion check, reported per check. Free, no credential required, always.
Only reads 6Show 6 read-only tools
  • get_certificateFetch the signed fairness certificate for a finished deal (state CERTIFIED).1 finding

    Why it is in this group

    • The name "get_certificate" says "get": a word for reading.

    Findings

    Description, as the server wrote it
    Fetch the signed fairness certificate for a finished deal (state CERTIFIED). Includes the labelled signature (es256 or ed25519) and transparency-log inclusion proof. Verify it with verify_certificate.
  • get_dealRead a deal's public state: protocol state (OPEN/COMMITTING/REVEALING/CERTIFIED/VOID/EXPIRED), who has committed/revealed, deadlines, result, and certificate_id once issued.1 finding

    Why it is in this group

    • The name "get_deal" says "get": a word for reading.

    Findings

    Description, as the server wrote it
    Read a deal's public state: protocol state (OPEN/COMMITTING/REVEALING/CERTIFIED/VOID/EXPIRED), who has committed/revealed, deadlines, result, and certificate_id once issued. Inputs of other parties are never exposed.
  • get_entropyFinish a random.v1 deal once every party has revealed: redeal fetches the deal's pre-declared drand round from the public League of Entropy beacon (fixed at creation, publicly cros…Reads text others write1 finding

    Why it is in this group

    • The name "get_entropy" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.

    Findings

    Description, as the server wrote it
    Finish a random.v1 deal once every party has revealed: redeal fetches the deal's pre-declared drand round from the public League of Entropy beacon (fixed at creation, publicly cross-checkable), computes the draw, and issues the certificate. Call this after the last reveal_input; the deal rests in REVEALING until you do. Idempotent — safe to retry.
  • get_public_certificateFetch a certificate's full JSON (outcome included) by id.No findings

    Why it is in this group

    • The name "get_public_certificate" says "get": a word for reading.
    Description, as the server wrote it
    Fetch a certificate's full JSON (outcome included) by id. Works for public deals (the default). Parties-only deals and unknown ids both return NOT_FOUND. To re-verify the computation itself, use verify_certificate (checks) or the CLI re-runner with the parties' inputs.
  • list_algorithmsList redeal's algorithms (split.v1 fixed-budget fair division, random.v1 verifiable random selection, shapley.v1 Shapley shares, auction.v1 sealed-bid second-price auctions) with t…No findings

    Why it is in this group

    • The name "list_algorithms" says "list": a word for reading.
    Description, as the server wrote it
    List redeal's algorithms (split.v1 fixed-budget fair division, random.v1 verifiable random selection, shapley.v1 Shapley shares, auction.v1 sealed-bid second-price auctions) with their input contracts and the published test vectors (served inline — the same fixtures the engine test suite runs). Read this before creating a deal.
  • validate_inputValidate your algorithm input against the deal's contract BEFORE you commit.No findings

    Why it is in this group

    • The name "validate_input" says "validate": a word for reading.
    Description, as the server wrote it
    Validate your algorithm input against the deal's contract BEFORE you commit. A commitment binds the exact input bytes — a contract-violating input (e.g. split.v1 valuations not summing to exactly 1000) can never be corrected afterwards and the deal will VOID at the reveal deadline. Always validate first, then compute_commitment_tool, then commit_input. Read-only: nothing is stored or changed.

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 or outbound.

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 out0
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, 18:52 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
6
Protocol version
2025-11-25
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 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.redeal.dev/mcp: tools/list returned 12 tools to an anonymous client, including commit_input (write), compute_commitment_tool (write), create_deal (write), create_key (write), reveal_input (write) and 1 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

4 info

History

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

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 0.7.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http redeal https://api.redeal.dev/mcp
claude mcp add --transport http redeal https://api.redeal.dev/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__redeal__get_certificate",
      "mcp__redeal__get_deal",
      "mcp__redeal__get_entropy",
      "mcp__redeal__get_public_certificate",
      "mcp__redeal__list_algorithms",
      "mcp__redeal__validate_input"
    ],
    "ask": [
      "mcp__redeal__commit_input",
      "mcp__redeal__compute_commitment_tool",
      "mcp__redeal__create_deal",
      "mcp__redeal__create_key",
      "mcp__redeal__reveal_input",
      "mcp__redeal__verify_certificate"
    ],
    "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 redeal. Review it before you use it.

Capability tags behind 1 rule
  • mcp__redeal__get_entropy untrusted-input

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/dev.redeal/redeal/verify?hash=b02af6228e7590a6e4a0ebbc68ba6c2383fd8983f088d0c69952572edd02a69a" | jq -e '.changed == false'

Pinned hash b02af6228e75, from Nov 11, 2026, 09:18 UTC.

Watch

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

https://radar.anlyon.com/servers/dev.redeal/redeal/changes.xml

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

Badge

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

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:12 UTC.

Redeal MCP server: questions and answers

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

Is the Redeal MCP server safe?

No scan can promise that. What its definitions show: 12 tools, 6 of which can change, send or delete something, and 4 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 Redeal MCP server delete data?

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

Can the Redeal 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 Redeal MCP server have?

12 tools: 6 write, 6 read. commit_input, compute_commitment_tool, create_deal, create_key, reveal_input, verify_certificate, get_certificate, get_deal and 4 more.

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

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

Does the Redeal MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Redeal MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.