Skip to content

kyde score MCP server

com.kyde/scorekyde.comstreamable-httpv0.12.0Scanned

Agent observability via OpenTelemetry: drift, loop and hijack alerts, e.g. after a prompt injection.

7 tools: 2 can delete or cancel things, 4 change things and 1 only read.

Tools: 2 delete, 0 irreversible, 4 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 2
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here can delete or cancel things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 kyde score MCP server can do

The kyde score MCP server is published by kyde.com, a domain the MCP Registry verified. It has 7 tools. It can delete or cancel things (2 tools: rebaseline and revoke_key) and create or change data (4 tools: create_key, set_webhook, claim_key and verify_agent). 1 tool only reads.

2 tools bring in text other people can write (claim_key and verify_agent); 2 tools can send data out of your system (create_key and set_webhook).

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 8 times since Anlyon Radar first saw them.

Last scanned Nov 18, 2026, version 0.12.0.

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

Deletes or cancels 2Claude Code: deny
  • rebaselineForget one agent's learned baseline and score and relearn from its next 30 runs over at least 3 days.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 destructive (destructiveHint: true).
    Description, as the server wrote it
    Forget one agent's learned baseline and score and relearn from its next 30 runs over at least 3 days. For intended behavior changes (new model, new task) that left the agent permanently deviating. The reset is permanently visible: records and alarms stay stored, the agent carries rebaselined_at, and the reset itself is recorded as a rebaseline alarm naming the score/band it erased. Requires confirm=true and the human's explicit go-ahead.

    Annotations the server declares

    • title: Reset agent baseline
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
  • revoke_keyRevoke the key and permanently delete all data stored under it.No findings

    Why it is in this group

    • The name "revoke_key" says "revoke": a word for removing or ending something.
    • The description says "permanently delete".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Revoke the key and permanently delete all data stored under it. Requires confirm=true.

    Annotations the server declares

    • title: Revoke key and delete data
    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
Changes things 4Claude Code: ask
  • claim_keyAttach your human's email to the key (double opt-in: Kyde mails a confirmation link).Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "attach": a word for a change.

    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
    Attach your human's email to the key (double opt-in: Kyde mails a confirmation link). Once confirmed, the key is claimed: the human gets the management dashboard, and rebaseline, webhook changes and revocation work only for them — no agent, including you, can reset its own score. Asking the human for the address once is a mandatory setup step; only the human may decline. Never invent or guess an address; skip only when get_scores already shows claimed: true.

    Annotations the server declares

    • title: Attach a human to the key
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
  • create_keyCreate a scoring key (no signup).Can send data outNo findings

    Why it is in this group

    • The name "create_key" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Create a scoring key (no signup). One key covers all agents, identified by OTel service.name. webhook_url (https) is optional but recommended: it receives an HMAC-signed POST when any agent's score changes band.

    Annotations the server declares

    • title: Create scoring key
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • set_webhookAdd or change the https webhook.Can send data outNo findings

    Why it is in this group

    • The name "set_webhook" says "set": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Add or change the https webhook. It is POSTed on every band change and rebaseline, HMAC-SHA256-signed with the scoring key (header x-kyde-signature: sha256=<hex> over the raw body).

    Annotations the server declares

    • title: Set alert webhook
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • verify_agentProve who is on the other end before delegating work: challenges the Shine ID at shine.kyde.com, waits for the agent to confirm over its own authenticated connection, then verifies…Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Prove who is on the other end before delegating work: challenges the Shine ID at shine.kyde.com, waits for the agent to confirm over its own authenticated connection, then verifies the Ed25519-signed statement against Shine's JWKS and compares the nonce hash. Needs no scoring key. The verified agent typically polls every 30 s, so a first call often answers 'pending' — call verify_agent again with the returned challenge_id, result_token and nonce to keep waiting. In the result, band 'learning' means identity confirmed but behavior not yet scored (still learning: 30 runs over at least 3 days): whether to delegate to a learning agent is the challenger's policy call.

    Annotations the server declares

    • title: Verify another agent (Shine)
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • get_scoresCurrent drift score per agent under the key: 0-39 deviating, 40-69 watch, 70-100 normal; status 'learning' until the baseline freezes (30 runs over at least 3 days).No findings

    Why it is in this group

    • The name "get_scores" says "get": a word for reading.
    Description, as the server wrote it
    Current drift score per agent under the key: 0-39 deviating, 40-69 watch, 70-100 normal; status 'learning' until the baseline freezes (30 runs over at least 3 days). 'feedback' lists alerts to ask your human about (share answer_url, never answer it yourself).

    Annotations the server declares

    • title: Get drift scores
    • readOnlyHint: 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.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
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.

Tools listed without sign-in

Looked at Nov 17, 2026, 15:22 UTC, unchanged since Nov 17, 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
6
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://score.kyde.com/.well-known/oauth-protected-resource/mcp
Authorization servers
https://score.kyde.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 6 tools that change things (2 destructive, 4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://score.kyde.com/mcp: tools/list returned 7 tools to an anonymous client, including rebaseline (destructive), revoke_key (destructive), create_key (write), set_webhook (write), claim_key (write) and 1 more

    What this check looks for

Posture changes

  1. Nov 17, 2026
    • Tools that change things, listed without credentials: 5 to 6
  2. Nov 10, 2026
    • Tools that change things, listed without credentials: 3 to 5
    • RFC 9728 protected resource metadata: none to https://score.kyde.com/.well-known/oauth-protected-resource/mcp
    • Authorization servers: none to https://score.kyde.com
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to 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.

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 5 -> 6.View diff
    • Tools that change things, listed without credentials: 5 to 6
  2. Tools2 changed.~2 changedView diff
  3. Tools1 changed.~1 changedView diff
  4. Tools1 added.+1 addedView diff
  5. Tools1 changed.~1 changedView diff
  6. PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 5; RFC 9728 protected resource metadata: none -> https://score.kyde.com/.well-known/oauth-protected-resource/mcp; Authorization servers: none -> https://scor…View diff
    • Tools that change things, listed without credentials: 3 to 5
    • RFC 9728 protected resource metadata: none to https://score.kyde.com/.well-known/oauth-protected-resource/mcp
    • Authorization servers: none to https://score.kyde.com
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to no
  7. Tools1 changed.~1 changedView diff
  8. Tools2 changed.~2 changedView diff
  9. Tools1 added, 3 changed.+1 added~3 changedView diff
  10. Tools1 added.+1 addedView diff

Install

Pinned to version 0.12.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http score https://score.kyde.com/mcp
claude mcp add --transport http score https://score.kyde.com/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__score__get_scores"
    ],
    "ask": [
      "mcp__score__create_key",
      "mcp__score__set_webhook",
      "mcp__score__claim_key",
      "mcp__score__verify_agent"
    ],
    "deny": [
      "mcp__score__rebaseline",
      "mcp__score__revoke_key"
    ]
  }
}

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 score. Review it before you use it.

Capability tags behind 4 rules
  • mcp__score__create_key outbound
  • mcp__score__set_webhook outbound
  • mcp__score__claim_key untrusted-input
  • mcp__score__verify_agent 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/com.kyde/score/verify?hash=3774365b8269ddfce328257caac7b94bb3a6d9bdf6398460519e41134fa2bd00" | jq -e '.changed == false'

Pinned hash 3774365b8269, from Nov 18, 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.kyde/score/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.kyde/score
[![Anlyon Radar](https://radar.anlyon.com/badge/com.kyde/score.svg)](https://radar.anlyon.com/servers/com.kyde/score)

Source: MCP Registry. Synced Nov 18, 2026, 20:17 UTC.

kyde score MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the kyde score MCP server safe?

No scan can promise that. What its definitions show: 7 tools, 6 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 kyde score MCP server delete data?

Yes. 2 tools can delete, cancel or revoke something: rebaseline and revoke_key.

Can the kyde score 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 kyde score MCP server have?

7 tools: 2 destructive, 4 write, 1 read. rebaseline, revoke_key, create_key, set_webhook, claim_key, verify_agent and get_scores.

Does the kyde score MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the kyde score MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_key and set_webhook.

Has the kyde score MCP server changed its tools?

Yes, 8 times since Anlyon Radar started tracking it, most recently on Nov 14, 2026. Every change is on this page and in its Atom feed.