PreReason MCP server
com.prereason/mcpprereason.comstreamable-httpv0.9.1Scanned
Financial market context for AI agents, with listed companies' results: www.prereason.com/agents.md
7 tools: 7 only read.
- Reads private data · 1
- Reads text others write · 0
- 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 PreReason MCP server can do
The PreReason MCP server is published by prereason.com, a domain the MCP Registry verified. It has 7 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool reads private data (get_context).
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, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 9, 2026, version 0.9.1.
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
get_changesWhat changed since your last call: the change events PreReason records.No findings
Why it is in this group
- The name "get_changes" says "get": a word for reading.
Description, as the server wrote it What changed since your last call: the change events PreReason records. A live briefing's state label changing, a tracked release becoming known, and, for the companies you name, figures stored for a newer period, an event driven situation turning on, and filed news. Each event says what changed, when it happened, when PreReason knew it and where to read it next (the briefing or metric to fetch with get_context or get_metric); it carries no value. For the filed and official records themselves, by date, use get_news. Pass the next_cursor of your previous call to read only what is new; without one, the last 24 hours. Needs a PreReason account with basic access or above: a signed in connection or an API key.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_contextGet a pre-reasoned market briefing with trends and confidence scores, plus regime classification and a rule based note on what moved with the price in the briefings that carry them…Reads private dataNo findings
Why it is in this group
- The name "get_context" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "note": it reads notes.
Description, as the server wrote it Get a pre-reasoned market briefing with trends and confidence scores, plus regime classification and a rule based note on what moved with the price in the briefings that carry them, for the requested domain (macro, rates, bonds, FX, commodities, a listed company, cross-asset or Bitcoin; the same families as the server instructions). Output is written to be read directly by reasoning agents, not parsed for individual values. Find the briefing id with list_briefings first, which also gives each briefing's plan; for one data series rather than a briefing, use get_metric. Needs a PreReason account: a signed in connection or an API key.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_healthCheck API health status, version, and available endpoints.No findings
Why it is in this group
- The name "get_health" says "get": a word for reading.
Description, as the server wrote it Check API health status, version, and available endpoints. Use it to confirm the server answers or to read its version; it carries no market data, so use list_briefings or list_metrics to find data. No authentication required.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_metricGet a single metric with pre-reasoned signal interpretation, trend analysis (7d/30d/90d), confidence score with factor breakdown, momentum, and percentile ranking.No findings
Why it is in this group
- The name "get_metric" says "get": a word for reading.
Description, as the server wrote it Get a single metric with pre-reasoned signal interpretation, trend analysis (7d/30d/90d), confidence score with factor breakdown, momentum, and percentile ranking. Name the metric; list_metrics lists them and searches them by word. Needs a PreReason account: a signed in connection or an API key. Returns analyzed context (signal, trend direction, momentum, percentile among every stored daily close), not raw values. The signal is bullish, bearish or neutral on crypto series, and above-trend, below-trend or at-trend on every other metric, where the value sits against its trend, so a high yield reads above-trend. Use it to read where a metric stands against its trend and its own history, not just its number; for a reasoned view across several series, use get_context with a briefing. Every plan reads each metric's latest reading. Pro and above read every metric in full; on other plans, a metric outside the plan returns its latest reading only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_newsDated records of what companies filed and what federal agencies and the Federal Reserve published, newest first, each with its source, its date or time and a link.No findings
Why it is in this group
- The name "get_news" says "get": a word for reading.
Description, as the server wrote it Dated records of what companies filed and what federal agencies and the Federal Reserve published, newest first, each with its source, its date or time and a link. Name a company in `about` for its filings alone; `kind` narrows to filed or official records; `since` and `until`, or `as_of`, set the window. Every answer names the sources it read. It states records, not reasons. For what changed since your last call, use get_changes; this tool reads the records themselves, by date. Needs a PreReason account: a signed in connection or an API key.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_briefingsList the pre-reasoned market briefings, each with its tier requirement, and the company briefing (equities.company), one listed company per call.No findings
Why it is in this group
- The name "list_briefings" says "list": a word for reading.
Description, as the server wrote it List the pre-reasoned market briefings, each with its tier requirement, and the company briefing (equities.company), one listed company per call. Covers macro, rates, bonds, FX, commodities, listed companies, cross-asset and Bitcoin. Call it first to find the briefing id for a question, then read that briefing with get_context. Pass search with the question's words to get only the briefings that match, best first; when it names a company, the answer also lists the matching covered companies, each with the entity to pass to get_context. For one data series rather than a briefing, use list_metrics. Every covered company, by market, is listed at GET https://api.prereason.com/api/companies, with no key needed. No authentication required.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_metricsList the individual metrics, among them the Fed balance sheet, M2 supply, Treasury yields, net liquidity, the dollar, cross-asset indices (SPY, QQQ, VXX, UUP) and Bitcoin price and…No findings
Why it is in this group
- The name "list_metrics" says "list": a word for reading.
Description, as the server wrote it List the individual metrics, among them the Fed balance sheet, M2 supply, Treasury yields, net liquidity, the dollar, cross-asset indices (SPY, QQQ, VXX, UUP) and Bitcoin price and hash rate. Use it to find a metric's name for get_metric; for a reasoned view across several series, use list_briefings. Filter by category or by a search word. No authentication required.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
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 untrusted-input or outbound.
- Reads private data1
- 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 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, 18:44 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
- https://api.prereason.com/.well-known/oauth-protected-resource/api/mcp
- Authorization servers
- https://api.prereason.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
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.
Tools3 changed.~3 changedView diff
- Changed:get_changesOnly readsinputSchema
- Changed:get_contextOnly readsinputSchema
- Changed:get_metricOnly readsinputSchema
Tools3 changed.~3 changedView diff
- Changed:get_changesOnly readsinputSchema
- Changed:get_contextOnly readsdescriptioninputSchema
- Changed:get_metricOnly readsdescription
Install
Pinned to version 0.9.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http prereason https://api.prereason.com/api/mcpclaude mcp add --transport http prereason https://api.prereason.com/api/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__prereason__list_briefings",
"mcp__prereason__list_metrics",
"mcp__prereason__get_health",
"mcp__prereason__get_context",
"mcp__prereason__get_metric",
"mcp__prereason__get_changes",
"mcp__prereason__get_news"
],
"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 prereason. Review it before you use it.
Capability tags behind 1 rule
- mcp__prereason__get_context private-data
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/com.prereason/mcp/verify?hash=06749690fb4653195d455951b26921ce673937ecf744e5d17c409b6a7f9b60d9" | jq -e '.changed == false'Pinned hash 06749690fb46, from Nov 9, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.prereason/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.prereason/mcp)Source: MCP Registry · repository. Synced Oct 28, 2026, 03:17 UTC.
PreReason MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the PreReason 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 PreReason MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the PreReason 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 PreReason MCP server have?
- 7 tools: 7 read. list_briefings, list_metrics, get_health, get_context, get_metric, get_changes and get_news.
Does the PreReason MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the PreReason MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the PreReason MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.