Agent Provider Depot MCP server
com.getagentdepot/agent-provider-depotgetagentdepot.comstreamable-httpv0.17.56Scanned
One no-key call picks your agent's LLM, sandbox, search, email or DB provider, with sourced prices.
4 tools: 4 change things.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 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 Agent Provider Depot MCP server can do
The Agent Provider Depot MCP server is published by getagentdepot.com, a domain the MCP Registry verified. It has 4 tools. It can create or change data (4 tools: session_brief, rescue, decide and depot), but cannot delete data. None of its tools only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
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 6 times since Anlyon Radar first saw them.
Last scanned Nov 21, 2026, version 0.17.56.
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.
4 tools
Changes things 4Claude Code: ask
decideFirst pick, no key, before writing integration code (LLM, sandbox, search, email, DB).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 First pick, no key, before writing integration code (LLM, sandbox, search, email, DB). First call: {task:'run untrusted Python in a sandbox', roleId:'acme-support-agent'} (or X-Agent-Id; pick comes back either way, only labelled calls are counted; use a role, never a person's name). Returns the Depot Pick, runner-up, sourced price, when to skip it, reportOutcome, recheck. Recheck: since=recheck.since. Live API error: rescue. Stack changes since last cursor: session_brief. For quotes, compare, audit, freshness or to report an outcome: depot.
Annotations the server declares
- title: Pick a provider
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
depotCatalog reads and outcome reports: quotes, compare, audit, freshness.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.
Description, as the server wrote it Catalog reads and outcome reports: quotes, compare, audit, freshness. Use for those and to report an outcome. Not for a first pick (decide), a live API error (rescue), or stack changes since your last cursor (session_brief). Only report_outcome writes state; every other op is a read. Ops: prices: quote estimate compare free. Audit: check audit_repo freshness changes stack_delta coverage failures. Map: stack bundle search kit answer. Write: report_outcome. op=help lists args.
Annotations the server declares
- title: Depot drill-down
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
rescueLive API errors: paste the exact error (429, 402, 529, insufficient_quota, model_not_found) and provider id.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 Live API errors: paste the exact error (429, 402, 529, insufficient_quota, model_not_found) and provider id. Returns cause, fix and fallback, or checks to run. First pick: decide. Stack changes since last cursor: session_brief. Quotes/compare/audit/freshness/outcomes: depot.
Annotations the server declares
- title: Rescue a failing API call
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
session_briefStack changes since your last cursor (retired models, prices, packages, picks).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 Stack changes since your last cursor (retired models, prices, packages, picks). Send provider, model and package ids (never a manifest) plus that cursor. Returns clear|changed|attention, ≤3 sourced actions, a new cursor. First pick: decide. Live API error: rescue. Quotes/compare/audit/freshness/outcomes: depot.
Annotations the server declares
- title: Every-session brief
- 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 untrusted-input or outbound.
- 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 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 21, 2026, 19:23 UTC, unchanged since Nov 21, 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
- 4
- 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 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://getagentdepot.com/mcp: tools/list returned 4 tools to an anonymous client, including session_brief (write), rescue (write), decide (write), depot (write)
Posture changes
- Nov 7, 2026
- Tools that change things, listed without credentials: 3 to 4
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.
Tools1 changed.~1 changedView diff
- Changed:decideChanges thingsdescription
Tools1 changed.~1 changedView diff
- Changed:decideChanges thingsdescriptioninputSchema
Tools4 changed.~4 changedView diff
- Changed:decideChanges thingsdescriptioninputSchema
- Changed:depotChanges thingsdescriptioninputSchema
- Changed:rescueChanges thingsdescriptioninputSchema
- Changed:session_briefChanges thingsdescriptioninputSchema
Tools1 changed.~1 changedView diff
- Changed:decideChanges thingsdescription
Tools3 changed.~3 changedView diff
- Changed:decideChanges thingsdescription
- Changed:rescueChanges thingsdescription
- Changed:session_briefChanges thingsdescription
PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 4.View diff
- Tools that change things, listed without credentials: 3 to 4
Tools4 changed.~4 changedView diff
- Changed:decideChanges thingsdescriptioninputSchema
- Changed:depotChanges thingsdescriptioninputSchemaannotations
- Changed:rescueChanges thingsdescription
- Changed:session_briefChanges thingsdescription
Install
Pinned to version 0.17.56. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-provider-depot https://getagentdepot.com/mcpclaude mcp add --transport http agent-provider-depot https://getagentdepot.com/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__agent-provider-depot__session_brief",
"mcp__agent-provider-depot__rescue",
"mcp__agent-provider-depot__decide",
"mcp__agent-provider-depot__depot"
],
"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 agent-provider-depot. Review it before you use it.
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.getagentdepot/agent-provider-depot/verify?hash=d3c67963dcde14ec13f35c2e731b8f62be252bbbeec1be6b42598847631831a7" | jq -e '.changed == false'Pinned hash d3c67963dcde, from Nov 21, 2026, 15:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.getagentdepot/agent-provider-depot/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.getagentdepot/agent-provider-depot)Source: MCP Registry. Synced Nov 21, 2026, 16:17 UTC.
Agent Provider Depot MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Provider Depot MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 4 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 Agent Provider Depot MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Provider Depot 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 Agent Provider Depot MCP server have?
- 4 tools: 4 write. session_brief, rescue, decide and depot.
Does the Agent Provider Depot MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Provider Depot MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Agent Provider Depot MCP server changed its tools?
- Yes, 6 times since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.