PRG Risk Oracle MCP server
io.github.dsrpt1/prg-risk-oracledsrpt1streamable-httpv0.1.5Scanned
Market regime, 7-dimension risk vectors and payment hazard grades. Abstains when data is thin.
5 tools: 2 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 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.
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 PRG Risk Oracle MCP server can do
The PRG Risk Oracle MCP server is published by the GitHub account dsrpt1. It has 5 tools. It can create or change data (2 tools: get_alerts and check_counterparty), but cannot delete data. 3 tools only read.
1 tool can send data out of your system (check_counterparty).
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.
Last scanned Nov 19, 2026, version 0.1.5.
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.
5 tools
Changes things 2Claude Code: ask
check_counterpartyPre-audit a payment-gated endpoint before you buy from it.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Pre-audit a payment-gated endpoint before you buy from it. Two tiers, neither of which pays the endpoint: a live unpaid probe (challenge parse, scheme, latency, per-probe pass/fail, endpoint grade), and the on-chain settlement history of the offer's payee (has this address ever actually collected, how recently, how often). [paid: $0.50 USDC on Base]
get_alertsOpen PRG risk alert records, optionally filtered to those newer than a timestamp.No findings
Why it is in this group
- The name "get_alerts" says "get": a word for reading.
- The description's first verb is "open": a word for a change.
Description, as the server wrote it Open PRG risk alert records, optionally filtered to those newer than a timestamp. [paid: $0.02 USDC on Base]
Only reads 3Show 3 read-only tools
get_mhiMachine Hazard Index reading for a payment rail, facilitator, or endpoint, with component letter-grades and abstention status.No findings
Why it is in this group
- The name "get_mhi" says "get": a word for reading.
Description, as the server wrote it Machine Hazard Index reading for a payment rail, facilitator, or endpoint, with component letter-grades and abstention status. [free] (free while the MHI methodology stamps its output pre-calibration; moves to $0.05 on a calibrated release (SPEC §5.3))
get_regimeCurrent PRG market risk regime label and composite score band.No findings
Why it is in this group
- The name "get_regime" says "get": a word for reading.
Description, as the server wrote it Current PRG market risk regime label and composite score band. Free, rate-limited. [free] (free tier, rate-limited per IP)
get_risk_snapshotPRG composite risk score plus the seven dimension-level scores (INT, FRG, PRE, THR, PRO, REC, VAL) for one instrument or the market.No findings
Why it is in this group
- The name "get_risk_snapshot" says "get": a word for reading.
Description, as the server wrote it PRG composite risk score plus the seven dimension-level scores (INT, FRG, PRE, THR, PRO, REC, VAL) for one instrument or the market. [paid: $0.05 USDC on Base]
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 untrusted-input.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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.
Looked at Nov 20, 2026, 19:04 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
- 2
- 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://prg-risk-mcp-production.up.railway.app/mcp: tools/list returned 5 tools to an anonymous client, including get_alerts (write), check_counterparty (write)
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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.5. Values in angle brackets are yours to fill in.
claude mcp add --transport http prg-risk-oracle https://prg-risk-mcp-production.up.railway.app/mcpclaude mcp add --transport http prg-risk-oracle https://prg-risk-mcp-production.up.railway.app/mcpRun 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.
{
"permissions": {
"allow": [
"mcp__prg-risk-oracle__get_regime",
"mcp__prg-risk-oracle__get_risk_snapshot",
"mcp__prg-risk-oracle__get_mhi"
],
"ask": [
"mcp__prg-risk-oracle__get_alerts",
"mcp__prg-risk-oracle__check_counterparty"
],
"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 prg-risk-oracle. Review it before you use it.
Capability tags behind 1 rule
- mcp__prg-risk-oracle__check_counterparty 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/io.github.dsrpt1/prg-risk-oracle/verify?hash=5882c7fe07c397b66a91d25e22d0ae136057bdde10ab4513bd83bf6ae1ccd168" | jq -e '.changed == false'Pinned hash 5882c7fe07c3, from Nov 19, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.dsrpt1/prg-risk-oracle/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.dsrpt1/prg-risk-oracle)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:33 UTC.
PRG Risk Oracle MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the PRG Risk Oracle MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 2 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 PRG Risk Oracle MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the PRG Risk Oracle 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 PRG Risk Oracle MCP server have?
- 5 tools: 2 write, 3 read. get_alerts, check_counterparty, get_regime, get_risk_snapshot and get_mhi.
Does the PRG Risk Oracle MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the PRG Risk Oracle 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): check_counterparty.
Has the PRG Risk Oracle MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.