Signal Oracle MCP server
io.github.NeruoticFarrow/signal-oracleNeruoticFarrowstreamable-httpv1.0.0Scanned
Pay-per-call change-intelligence feeds for AI agents over x402 (deps, security, regs, tariffs)
7 tools: 7 only read.
- Reads private data · 2
- Reads text others write · 6
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 Signal Oracle MCP server can do
The Signal Oracle MCP server is published by the GitHub account NeruoticFarrow. It has 7 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
2 tools read private data (preview_feed and depwatch_preview); 6 tools bring in text other people can write (preview_feed, packagehealth_preview, vendorrisk_preview and 3 more).
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 16, 2026, version 1.0.0.
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.
7 tools
Only reads 7Show 7 read-only tools
depwatch_previewFree preview of breaking changes / new releases for a software dependency.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "depwatch_preview" says "preview": a word for reading.
What it can reach
- private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free preview of breaking changes / new releases for a software dependency. Pass an npm/PyPI `package` (resolved and fetched live if not already tracked) or a GitHub `repo` (owner/repo). Returns up to 5 recent changes plus the package's current version. Full history, significance filtering, and the LLM brief are paid via x402.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
list_feedsList every change-intelligence feed: source slug, label, the question each answers, per-call prices, paid x402 endpoints, and free discovery URLs.No findings
Why it is in this group
- The name "list_feeds" says "list": a word for reading.
Description, as the server wrote it List every change-intelligence feed: source slug, label, the question each answers, per-call prices, paid x402 endpoints, and free discovery URLs. There are ~120 feeds, so pass `category` to filter (e.g. 'security', 'regulatory', 'packages', 'premium', 'infrastructure', 'compliance') and/or `compact: true` to keep the payload small. Use the returned `source` slug with preview_feed.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
packagehealth_previewFREE preview of a dependency's health: current version, deprecation flag, OpenSSF Scorecard, SPDX license, and known-advisory count (via deps.dev).Reads text others writeNo findings
Why it is in this group
- The name "packagehealth_preview" says "preview": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it FREE preview of a dependency's health: current version, deprecation flag, OpenSSF Scorecard, SPDX license, and known-advisory count (via deps.dev). The full ship/avoid verdict — per-advisory CISA-KEV active-exploit cross-reference, license-fit judgement, and LLM recommendation — is the paid /v1/packagehealth/check.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
preview_feedFree preview (up to 5 recent changes) for any feed.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "preview_feed" says "preview": a word for reading.
What it can reach
- private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free preview (up to 5 recent changes) for any feed. Pass the feed's `source` slug (from list_feeds). Optionally: `since` (ISO-8601) to window; `scope` to filter to an entity-id prefix on feeds that support it (e.g. an HTS code); or `package`/`repo`/`ecosystem` on feeds that resolve arbitrary entities live (e.g. dependency feeds). The full feed, status, and LLM brief are paid via x402.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
regwatch_previewFree preview of recent Federal Register regulatory actions in the tracked industry vertical.Reads text others writeNo findings
Why it is in this group
- The name "regwatch_preview" says "preview": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free preview of recent Federal Register regulatory actions in the tracked industry vertical. Returns up to 5 recent items. The full windowed feed and the LLM brief are paid via x402.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
tariffwatch_previewFree preview of recent US import-tariff changes.Reads text others writeNo findings
Why it is in this group
- The name "tariffwatch_preview" says "preview": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free preview of recent US import-tariff changes. Optionally scope to an HTS code prefix (e.g. '6109' or '8471.30'). Returns up to 5 recent changes plus current duty-rate state for a scoped code. Full feed and the LLM brief are paid via x402.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
vendorrisk_previewFREE preview of counterparty risk: tracked OFAC designations + product recalls we monitor for the name.Reads text others writeNo findings
Why it is in this group
- The name "vendorrisk_preview" says "preview": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it FREE preview of counterparty risk: tracked OFAC designations + product recalls we monitor for the name. The authoritative sanctions/denied-party (CSL) + federal debarment (SAM) screening and the CLEAR→PROHIBITED risk verdict are the paid /v1/vendorrisk/check.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
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 outbound.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write6
- 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.
Looked at Nov 20, 2026, 18:59 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
- 0
- 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
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 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http signal-oracle https://oracles-production.up.railway.app/mcpclaude mcp add --transport http signal-oracle https://oracles-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__signal-oracle__list_feeds",
"mcp__signal-oracle__preview_feed",
"mcp__signal-oracle__packagehealth_preview",
"mcp__signal-oracle__vendorrisk_preview",
"mcp__signal-oracle__depwatch_preview",
"mcp__signal-oracle__regwatch_preview",
"mcp__signal-oracle__tariffwatch_preview"
],
"ask": [],
"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 signal-oracle. Review it before you use it.
Capability tags behind 6 rules
- mcp__signal-oracle__preview_feed private-data, untrusted-input
- mcp__signal-oracle__packagehealth_preview untrusted-input
- mcp__signal-oracle__vendorrisk_preview untrusted-input
- mcp__signal-oracle__depwatch_preview private-data, untrusted-input
- mcp__signal-oracle__regwatch_preview untrusted-input
- mcp__signal-oracle__tariffwatch_preview 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/io.github.NeruoticFarrow/signal-oracle/verify?hash=735fb727602a37169eff8f2cdaeb770c9b678e3cb208025952dc6398457b2928" | jq -e '.changed == false'Pinned hash 735fb727602a, from Nov 16, 2026, 02:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.NeruoticFarrow/signal-oracle/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.NeruoticFarrow/signal-oracle)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:18 UTC.
Signal Oracle MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Signal Oracle MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the Signal 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 Signal 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 Signal Oracle MCP server have?
- 7 tools: 7 read. list_feeds, preview_feed, packagehealth_preview, vendorrisk_preview, depwatch_preview, regwatch_preview and tariffwatch_preview.
Does the Signal Oracle MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Signal Oracle MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Signal Oracle MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.