Provably Fair Giveaway MCP — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Replayable random selection bound to a public randomness beacon: Do published commitments and entrant ordering remain sufficient to replay each draw independently?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Commit-and-reveal raffle/giveaway winner selection using public drand randomness.

What we know

Package description identifies a provably-fair random-selection MCP that commits before the draw and uses the public drand beacon so anyone can verify the winner selection.

Maintenance / activity evidence

provably-fair-mcp 1.0.4 published 2026-08-09T01:51:57.416Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: low.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Random-selection authority; exact persistence/publication behavior unresolved. Complete write authority is not verified.
Authentication not yet verified.
Sensitive access: Participant identifiers/list

Randomness can be verifiable while input list or publication workflow is still wrong; insufficient first-party evidence.

Full authority, access and evidence limits are available in Review context and Access & risk.

All limitations / Review context

Do published commitments and entrant ordering remain sufficient to replay each draw independently?

The bounded review of the publisher's documented Replayable random selection bound to a public randomness beacon and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

Randomness can be verifiable while input list or publication workflow is still wrong; insufficient first-party evidence.
Random-selection authority; exact persistence/publication behavior unresolved.
Participant lists and draw metadata may be processed locally/remotely; retention unknown.
Sensitive access: Participant identifiers/list
Complete write authority is not verified.
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
publisher identity
official repository/docs
auth
commitment persistence
data retention
complete tools
First-party website/repository documentation was not recovered.
Exact commitment storage, participant-data handling, install/auth and whether draws write public records remain unresolved.
Provable randomness does not guarantee fair participant-list construction.

Original activity observations

provably-fair-mcp 1.0.4 published 2026-08-09T01:51:57.416Z

Technical identity

npm/provably-fair-mcp

Exact implementation source: https://www.npmjs.com/package/provably-fair-mcp ↗
Reviewed resource type: MCP Server
Package identity: npm:provably-fair-mcp

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 8, 2026

Package registry ↗
provably-fair-mcp
Recorded package identity, distribution or download evidence.
Includes references whose attribution is not established.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Documentation entry — installation instructions still need review.

Warning

No runtime server process, Docker setup, OAuth or credentials were executed during this research.
Identity-to-install artifact mismatch still unresolved; avoid one-click install.
Install documentation is not a guarantee of current package/runtime compatibility.
Publisher README gives working-style client configuration but uses GitHub repository spec instead of exact published npm identity. Same publisher naming does not prove artifact equivalence.
2026-10-13 targeted publisher npm README plus official repository/docs where specified; static research, not runtime test.
Never paste real credentials into a documentation example.
No live install, OAuth, paid calls, third-party mutation or credential revocation executed.
Some host removal commands are MCP100-composed based on chosen registration name, not publisher-authored.

Install / connect · artifact equivalence unresolved
Publisher-documented package/connection route; replace placeholders and verify host-specific syntax.
Configure / authenticate
MCP100 setup guide
Official client JSON: stdio command npx args ["-y","github:promptcoinapp/provably-fair-mcp"]. Keep the Radar identity npm/provably-fair-mcp unchanged and flag that this invocation fetches GitHub, not necessarily the published npm tarball. Pin to reviewed commit before production.
Use correct transport and published host config. Never paste secrets in chat; server registration is separate from software installation.
Check connection
Suggested check
Confirm available verification tools in client; run only non-transactional verification.
Remove / uninstall / revoke
MCP100 setup guide
If registered as `provably-fair-mcp` in Claude Code, remove its exact client entry with `claude mcp remove provably-fair-mcp`; for Cursor/Claude Desktop/Codex, remove the matching MCP entry in that host settings. This client removal is MCP100-composed, not a vendor uninstall instruction. Npx does not imply a global install; do not delete user data or revoke credentials implicitly.
Conditional host / package cleanup · Claude Code only · MCP100 composed guide
claude mcp remove provably-fair-mcp

Official Documentation & Sources

What it does

Package description identifies a provably-fair random-selection MCP that commits before the draw and uses the public drand beacon so anyone can verify the winner selection.

Capability: Productivity & Collaboration
Resource type: MCP Server
Best fit: Commit-and-reveal raffle/giveaway winner selection using public drand randomness.

Representative uses

Pick giveaway winners
Publish/verifiably reproduce a random draw
Use drand beacon as external randomness source

Limitations

First-party website/repository documentation was not recovered.
Exact commitment storage, participant-data handling, install/auth and whether draws write public records remain unresolved.
Provable randomness does not guarantee fair participant-list construction.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Not documented in the reviewed sources
Permissions: Random-selection authority; exact persistence/publication behavior unresolved.
Data handling: Participant lists and draw metadata may be processed locally/remotely; retention unknown.
Cost: unknown
Risk and cautions: Randomness can be verifiable while input list or publication workflow is still wrong; insufficient first-party evidence.

Access scope and cautions

Write actions: Not verified
Sensitive access: Participant identifiers/list
Risk level: moderate

The reviewed evidence does not establish the complete write authority of this MCP. Consult the unresolved evidence before granting write access.

FAQ

Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Pick giveaway winners; Publish/verifiably reproduce a random draw; Use drand beacon as external randomness source.

Can it modify data or perform write operations?

Not verified. The available evidence does not establish the complete write authority. Recorded permission context: Random-selection authority; exact persistence/publication behavior unresolved.

What data-handling boundary should I consider?

Participant lists and draw metadata may be processed locally/remotely; retention unknown. Recorded sensitive-access context: Participant identifiers/list.

What limitations and risks should I check before use?

Randomness can be verifiable while input list or publication workflow is still wrong; insufficient first-party evidence. First-party website/repository documentation was not recovered. Exact commitment storage, participant-data handling, install/auth and whether draws write public records remain unresolved. Provable randomness does not guarantee fair participant-list construction. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.