pumppill-mcpSAFE
Hosted MCP server: token safety and measured outcomes for Robinhood Chain and Solana
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Token intelligence for Robinhood Chain (chainId 4663) and Solana, and agentic trading on Robinhood Chain, served as a hosted Model Context Protocol server.
https://api.pumppill.org/mcp
Streamable HTTP. No key, no account, nothing to install for the read tools. Registry name: org.pumppill/token-safety (v1.4.0). How-to page:
This repository holds the connection instructions, example client configs and the registry manifest. The server itself is hosted by PumpPill; its source is not published here.
What it answers
The questions that cost people money: can this contract be sold, which contract is the real one behind a ticker, what has this deployer launched before, which wallets hold enough to move a pool, and what happened to the tokens PumpPill logged, with the losers counted.
And what is happening now: which tokens traders on the FOMO app are gathering on, with PumpPill's own risk read beside each one, and the calls PumpPill's room posted with how each has done since, losers included. whats_moving returns both, plus the newest flags, in one call.
Every result carries a cite string and a timestamp for when the read was taken. A token PumpPill has not read comes back as found: false, which means "not in the index", never "safe". Nothing here predicts a price or recommends a trade. Answers about a token carry a trade_link that opens it in PumpPill's Telegram trade bot; it is a place to trade, present on every token alike, not a pick.
And, with an agent key from the trade bot, your agent can trade: it checks a rule you built on pumppill.org/customize and buys new matches from your PumpPill trade bot wallet. PumpPill reads each token before any buy and refuses a red flag, your limits apply, and every or
293e1d60d2b2OBSERVED · 2026-10-11Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
streamable-http
Gates applied: no_behavioural_pass.
293e1d60d2b2full audit observations/trust-audit/mcp-server/jackedbased__pumppill-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 293e1d60d2b2 | SAFE | B | 89 | first audit |
Questions
What is the pumppill-mcp MCP server?
Hosted MCP server: token safety and measured outcomes for Robinhood Chain and Solana
Is pumppill-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does pumppill-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does pumppill-mcp run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (293e1d60d2b2), read on 2026-10-11. The repository is watched and re-audited when it changes.