yieldsentinel MCP server
io.github.agentsherpa/yieldsentinelagentsherpastreamable-httpv1.0.0Scanned
Policy check on a described yield position. Complement to yieldhunter. Research only.
2 tools: 2 change things.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- 1 finding
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 yieldsentinel MCP server can do
The yieldsentinel MCP server is published by the GitHub account agentsherpa. It has 2 tools. It can create or change data (2 tools: health and check_position), but cannot delete data. None of its tools only reads.
1 tool brings in text other people can write (check_position).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
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.
2 tools
Changes things 2Claude Code: ask
check_positionEvaluate a described stablecoin yield position against a research policy (pull).Reads text others write1 finding
Why it is in this group
- The description's first verb is "evaluate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "check_position" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "evaluate": a word for a change.
Description, as the server wrote it Evaluate a described stablecoin yield position against a research policy (pull). Always pass your policy rules (or a preset). Without a policy, no meaningful check is possible — the verdict will be review/unknown, never ok. Pass poolId from yieldhunter list_yields opportunities[].id (also accepted as opportunityId or id). That id is one market. Required for a real check: policyPreset (treasury-conservative | balanced-research | rwa-selective) and/or minScore / maxRewardShare / excludeCategories / maxExitRisk / requireCurated. Presets: treasury-conservative | balanced-research | rwa-selective. rwa-selective does not exclude RWA but is not a free pass (YS policy allowlist + higher bar). requireCurated uses the Yieldsentinel policy allowlist (curated.json), not yieldhunter scoring priors. Scoring ≠ policy approval. Fetches live yieldhunter research (score, APY, TVL, category, rewardShare, exitRisk) and curated flags, then returns a PolicyVerdict plus A2H (summary, suggestedNextSteps, legend). Incomplete or missing data is review/unknown — never a silent ok. A verdict is not an exit signal or execution order. Research only — never holds keys. Example: { "poolId": "43641cf5-a92e-416b-bce9-27113d3c0db6", "policyPreset": "treasury-conservative", "notionalUsd": 10000 }
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
healthLiveness and capability check for yieldsentinel (yieldsentinel.eth).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Liveness and capability check for yieldsentinel (yieldsentinel.eth). Returns service status, package version, health schemaVersion (separate from the tool-envelope schemaVersion), policyVersion, feature flags, and the list of available tools. toolStats counts all origins. toolStatsExternal is the external bucket. toolStatsInternal is the internal-test bucket. Send header X-YHYS-Test: 1 on every request (initialize, notifications, and each tools/call). On this stateless server that header is the only working internal-test marker. clientInfo.name prefixes yhys-qa / yhys-feel count only for the same request they appear in. May refresh research vintage via a yieldhunter health ping; a verdict still requires check_position. YH healthy ≠ YS ok. Use this first to verify connectivity, then call check_position with policyPreset treasury-conservative | balanced-research | rwa-selective (or explicit thresholds). Research estimates only — non-custodial; never holds keys or executes transactions. Example input: {}
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- 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 private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- 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, 19:01 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://yieldsentinel-agent-production.up.railway.app/mcp: tools/list returned 2 tools to an anonymous client, including health (write), check_position (write)
Findings
Matches of fixed checks, with the text they matched.
- Warncheck_position
The server marks "check_position" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "evaluate": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:check_positionChanges thingsdescriptioninputSchema
- Changed:healthChanges thingsdescription
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http yieldsentinel https://yieldsentinel-agent-production.up.railway.app/mcpclaude mcp add --transport http yieldsentinel https://yieldsentinel-agent-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": [],
"ask": [
"mcp__yieldsentinel__health",
"mcp__yieldsentinel__check_position"
],
"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 yieldsentinel. Review it before you use it.
Capability tags behind 1 rule
- mcp__yieldsentinel__check_position 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.agentsherpa/yieldsentinel/verify?hash=1c7d50950009d6701c42abe45c003b3bdd517c8a135c794a7fc384867d0c17fd" | jq -e '.changed == false'Pinned hash 1c7d50950009, from Nov 16, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.agentsherpa/yieldsentinel/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.agentsherpa/yieldsentinel)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:22 UTC.
yieldsentinel MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the yieldsentinel MCP server safe?
- No scan can promise that. What its definitions show: 2 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the yieldsentinel MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the yieldsentinel 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 yieldsentinel MCP server have?
- 2 tools: 2 write. health and check_position.
Does the yieldsentinel MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the yieldsentinel MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the yieldsentinel MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 2, 2026. Every change is on this page and in its Atom feed.