Skip to content

Agent Provider Depot MCP server

io.github.ethanhawkes-gif/agent-provider-depotethanhawkes-gifstreamable-httpv0.14.0Scanned

Dated picks, sourced pricing, and rescue/eval tools across 305 AI agent infrastructure providers.

4 tools: 4 change things.

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

Tools listed without sign-in. Remote posture

Anlyon alternative

4 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the Agent Provider Depot MCP server can do

The Agent Provider Depot MCP server is published by the GitHub account ethanhawkes-gif. 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 once since Anlyon Radar first saw them.

Last scanned Nov 10, 2026, version 0.14.0.

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.

4 tools

Changes things 4Claude Code: ask
  • decidePick a provider before writing integration code: LLM API, code sandbox, vector DB, web search, email, Postgres, auth, browser, observability.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
    Pick a provider before writing integration code: LLM API, code sandbox, vector DB, web search, email, Postgres, auth, browser, observability. First call e.g. {task:'run untrusted Python'}. Returns the dated Depot Pick, runner-up, sourced price, when to skip it, reportOutcome, recheck. Call again with since=recheck.since before adding a provider, on pick failure or after recheck.after (unchanged = short reply). Quotes: depot.

    Annotations the server declares

    • title: Pick a provider
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • depotOne op, args object: report_outcome(decision, provider, worked) after acting; quote(jtbd) SKU prices; estimate(jtbd, workload); compare(providers); free(jtbd); check(providers) dep…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
    One op, args object: report_outcome(decision, provider, worked) after acting; quote(jtbd) SKU prices; estimate(jtbd, workload); compare(providers); free(jtbd); check(providers) deprecated/retired flags; audit_repo(packages, models); stack(task), bundle(jtbds); search(q); kit(class); answer(task); stack_delta(providers, since); changes(since); failures; coverage; freshness. op=help lists args.

    Annotations the server declares

    • title: Depot drill-down
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • rescueDiagnose a failing third-party API call before you retry or swap: paste the exact error (429, 402, 529 overloaded, insufficient_quota, model_not_found, deprecated SDK) and provider…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
    Diagnose a failing third-party API call before you retry or swap: paste the exact error (429, 402, 529 overloaded, insufficient_quota, model_not_found, deprecated SDK) and provider id. Returns cause, fix and fallback route, or no match plus checks to run. Not for picking (decide).

    Annotations the server declares

    • title: Rescue a failing API call
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • session_briefSession start, if your code calls third-party APIs: what changed for your stack since your last call (retired models; price, package and pick changes).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
    Session start, if your code calls third-party APIs: what changed for your stack since your last call (retired models; price, package and pick changes). Send provider, model, package ids (never a manifest) and your last cursor. Returns clear|changed|attention, ≤3 actions (source, falsifier), a new cursor. New choice: decide. Live error: rescue.

    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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:24 UTC, unchanged since Oct 29, 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.

    Matched text

    https://getagentdepot.com/api/mcp: tools/list returned 4 tools to an anonymous client, including session_brief (write), rescue (write), decide (write), depot (write)

    What this check looks for

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. Tools3 added, 17 removed, 1 changed.+3 added−17 removed~1 changedView diff
    • Added:depotChanges things
    • Added:rescueChanges things
    • Added:session_briefChanges things
    • Removed:answer
    • Removed:audit_repo
    • Removed:bundle
    • Removed:changes
    • Removed:check
    • Removed:compare
    • Removed:coverage
    • Removed:estimate
    • Removed:failures
    • Removed:free
    • Removed:freshness
    • Removed:kit
    • Removed:quote
    • Removed:rescue_failure
    • Removed:search
    • Removed:stack
    • Removed:stack_delta
    • Changed:decideChanges thingstitledescriptioninputSchemaannotations

Install

Pinned to version 0.14.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-provider-depot https://getagentdepot.com/api/mcp
claude mcp add --transport http agent-provider-depot https://getagentdepot.com/api/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": [],
    "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/io.github.ethanhawkes-gif/agent-provider-depot/verify?hash=da294963072cc16c9c13894456471ee7049c4de4b7f894bcef4981fb10addd29" | jq -e '.changed == false'

Pinned hash da294963072c, from Nov 10, 2026, 09:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.ethanhawkes-gif/agent-provider-depot/changes.xml

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

Badge

Anlyon Radar badge for io.github.ethanhawkes-gif/agent-provider-depot
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.ethanhawkes-gif/agent-provider-depot.svg)](https://radar.anlyon.com/servers/io.github.ethanhawkes-gif/agent-provider-depot)

Source: MCP Registry · repository. Synced Nov 17, 2026, 15:18 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, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.