# Agent Provider Depot (remote · getagentdepot.com)

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

- Trust score: 73/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `getagentdepot.com`: 73/100 (this document), [markdown](https://verifymcp.io/servers/ethanhawkes-gif-agent-provider-depot/api-mcp.md), [page](https://verifymcp.io/servers/ethanhawkes-gif-agent-provider-depot/api-mcp)

## Channel facts

- Endpoint: `https://getagentdepot.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.14.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1276 tokens (~79/item across 16 items; 4 tools + 12 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 7 days we've observed: 17 tool removals, 0 breaking changes, 0 auth/transport breaks, 3 additions.
- **Tool Coverage**: 93/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 80% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Agent Provider Depot MCP server?

Agent Provider Depot is a hosted endpoint at https://getagentdepot.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ethanhawkes-gif-agent-provider-depot 'https://getagentdepot.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ethanhawkes-gif-agent-provider-depot": {
      "url": "https://getagentdepot.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ethanhawkes-gif-agent-provider-depot": {
      "type": "http",
      "url": "https://getagentdepot.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ethanhawkes-gif-agent-provider-depot]
url = "https://getagentdepot.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ethanhawkes-gif-agent-provider-depot": {
      "type": "remote",
      "url": "https://getagentdepot.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ethanhawkes-gif-agent-provider-depot --url 'https://getagentdepot.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ethanhawkes-gif-agent-provider-depot:
    url: "https://getagentdepot.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ethanhawkes-gif-agent-provider-depot": {
      "Transport": "http",
      "Url": "https://getagentdepot.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ethanhawkes-gif-agent-provider-depot -t streamable-http -u 'https://getagentdepot.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ethanhawkes-gif-agent-provider-depot": {
      "type": "http",
      "url": "https://getagentdepot.com/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 73, 0)

- [functional] Server version: 0.17.15 → 0.17.19

### 2026-11-04 (score 73, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “decide” rewrote its description, which is the text the model reads
- [functional] Server version: 0.17.6 → 0.17.15

### 2026-11-03 (score 73, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “decide” rewrote its description, which is the text the model reads
- [security] Tool “depot” rewrote its description, which is the text the model reads
- [security] Tool “rescue” rewrote its description, which is the text the model reads
- [security] Tool “session_brief” rewrote its description, which is the text the model reads
- [functional] Server version: 0.17.3 → 0.17.6
- [cosmetic] “decide” added an optional parameter “since”
- [cosmetic] “decide” reworded the description of “existing”
- [cosmetic] “decide” reworded the description of “jtbd”

### 2026-11-01 (score 73, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “decide” rewrote its description, which is the text the model reads
- [security] Tool “depot” rewrote its description, which is the text the model reads
- [security] Tool “session_brief” rewrote its description, which is the text the model reads
- [functional] Server version: 0.16.17 → 0.17.3

### 2026-10-31 (score 73, +1)

- [security] Resource “agents_md” now points somewhere else: /agents.md → https://getagentdepot.com/agents.md
- [security] Resource “benchmark” now points somewhere else: /api/benchmark → https://getagentdepot.com/api/benchmark
- [security] Resource “canonical” now points somewhere else: /api/canonical → https://getagentdepot.com/api/canonical
- [security] Resource “hub” now points somewhere else: /api/hub → https://getagentdepot.com/api/hub
- [security] Resource “jtbds” now points somewhere else: /api/jtbds → https://getagentdepot.com/api/jtbds
- [security] Resource “llms_txt” now points somewhere else: /llms.txt → https://getagentdepot.com/llms.txt
- [security] Resource “methodology” now points somewhere else: /api/methodology → https://getagentdepot.com/api/methodology
- [security] Resource “openapi” now points somewhere else: /openapi.yaml → https://getagentdepot.com/openapi.yaml
- [security] Resource “packs” now points somewhere else: /api/packs → https://getagentdepot.com/api/packs
- [security] Resource “privacy” now points somewhere else: /privacy → https://getagentdepot.com/privacy
- [security] Resource “skill_md” now points somewhere else: /skill.md → https://getagentdepot.com/skill.md
- [functional improvement] MCP protocol: fail → pass
- [functional] MCP protocol version: 2025-06-18 → 2026-07-28
- [functional] New resource “changelog”
- [functional] Server version: 0.16.9 → 0.16.17

### 2026-10-30 (score 72, +1)

- [security regression] Stability: unverified → fail
- [security regression] Tool “answer” was removed
- [security regression] Tool “audit_repo” was removed
- [security regression] Tool “bundle” was removed
- [security regression] Tool “changes” was removed
- [security regression] Tool “check” was removed
- [security regression] Tool “compare” was removed
- [security regression] Tool “coverage” was removed
- [security regression] Tool “estimate” was removed
- [security regression] Tool “failures” was removed
- [security regression] Tool “free” was removed
- [security regression] Tool “freshness” was removed
- [security regression] Tool “kit” was removed
- [security regression] Tool “quote” was removed
- [security regression] Tool “rescue_failure” was removed
- [security regression] Tool “search” was removed
- [security regression] Tool “stack” was removed
- [security regression] Tool “stack_delta” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] The server changed its declared name: io.github.ethanhawkes-gif/agent-provider-depot → com.getagentdepot/agent-provider-depot
- [security] Tool “decide” rewrote its description, which is the text the model reads
- [functional improvement] Tool coverage: 66% → 79%
- [functional improvement] Schema quality: 2087 → 1130
- [functional] Schema quality: fair → good
- [functional] New prompt “session-brief”
- [functional] Server version: 0.14.0 → 0.16.9
- [functional] New tool “depot”
- [functional] New tool “rescue”
- [functional] New tool “session_brief”
- [cosmetic] “decide” added an optional parameter “existing”
- [cosmetic] “decide” added an optional parameter “maxMonthly”
- [cosmetic] “decide” added an optional parameter “task”
- [cosmetic] “decide” reworded the description of “constraints”
- [cosmetic] “decide” reworded the description of “full”
- [cosmetic] “decide” reworded the description of “jtbd”
- [cosmetic] “decide” made “jtbd” optional
- [cosmetic] Tool “decide” changed its title: Depot decision card → Pick a provider

### 2026-10-29 (score 71)

First indexed and scored.

## MCP tools (4)

### `session_brief` (~159 tokens)

Every-session brief

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.

Input parameters:

- `cursor` (string): From your last brief
- `models` (array): Model ids you call
- `packages` (array): id or id@version
- `policies` (object)
- `providers` (array): e.g. anthropic, neon
- `stackFingerprint` (string): sha256:<64 hex>, hashed locally

### `rescue` (~132 tokens)

Rescue a failing API call

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).

Input parameters:

- `jtbd` (string): Job id
- `provider` (string): Provider id that failed
- `q` (string): Error text, status or SKU
- `sku` (string): Model or SKU id
- `status` (string): HTTP status, e.g. 429

### `decide` (~207 tokens)

Pick a provider

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.

Input parameters:

- `constraints` (string): Comma list, e.g. eu-region; may switch the pick
- `existing` (string): Provider ids you already use
- `full` (boolean)
- `jtbd` (string): Or a job id, e.g. agent-sandbox
- `maxMonthly` (number): USD budget for autoActOk
- `since` (string): Last recheck.since
- `task` (string): What you need, in words

### `depot` (~121 tokens)

Depot drill-down

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.

Input parameters:

- `args` (object)
- `op` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ethanhawkes-gif-agent-provider-depot/api-mcp#diagnostics

## Score history

- 2026-11-05: 73
- 2026-11-04: 73
- 2026-11-03: 73
- 2026-11-02: 73
- 2026-11-01: 73
- 2026-10-31: 73
- 2026-10-30: 72
- 2026-10-29: 71

## Common questions

### What is the Agent Provider Depot MCP server?

Agent Provider Depot is an MCP server listed in the public MCP registry as io.github.ethanhawkes-gif/agent-provider-depot. Dated picks, sourced pricing, and rescue/eval tools across 305 AI agent infrastructure providers. This page covers its hosted endpoint (https://getagentdepot.com/api/mcp).

### Is the Agent Provider Depot MCP server safe to use?

Agent Provider Depot scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Agent Provider Depot MCP server expose?

Agent Provider Depot exposes 4 tools: session_brief, rescue, decide, depot. Their descriptions and schemas cost roughly 619 tokens of context every time the server is loaded.

### Does the Agent Provider Depot MCP server require authentication?

No. We connected to Agent Provider Depot without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Agent Provider Depot MCP server still maintained?

Agent Provider Depot is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Agent Provider Depot MCP server?

VerifyMCP ran 13 checks on Agent Provider Depot, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://getagentdepot.com/api/mcp
- Repository: https://github.com/ethanhawkes-gif/agent-provider-depot
- Website: https://getagentdepot.com/
- Changelog RSS feed: https://verifymcp.io/servers/ethanhawkes-gif-agent-provider-depot/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ethanhawkes-gif-agent-provider-depot/api-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ethanhawkes-gif-agent-provider-depot/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ethanhawkes-gif-agent-provider-depot/api-mcp