# AI model deprecation and retirement dates, by provider (remote · referencesource.org)

Is this AI model id retired, when does it shut off, and what does its provider say replaces it?

- Trust score: 71/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `referencesource.org`: 71/100 (this document), [markdown](https://verifymcp.io/servers/org-referencesource-ai-model-retirement-dates/mcp-models.md), [page](https://verifymcp.io/servers/org-referencesource-ai-model-retirement-dates/mcp-models)

## Channel facts

- Endpoint: `https://referencesource.org/mcp/models`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-11-21.

- **Endpoint Security**: 74/100
  - 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.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 61/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1136 tokens (~378/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 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 AI model deprecation and retirement dates, by provider MCP server?

AI model deprecation and retirement dates, by provider is a hosted endpoint at https://referencesource.org/mcp/models, 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 org-referencesource-ai-model-retirement-dates 'https://referencesource.org/mcp/models'
```

### Cursor

```json
{
  "mcpServers": {
    "org-referencesource-ai-model-retirement-dates": {
      "url": "https://referencesource.org/mcp/models"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "org-referencesource-ai-model-retirement-dates": {
      "type": "http",
      "url": "https://referencesource.org/mcp/models"
    }
  }
}
```

### Codex

```toml
[mcp_servers.org-referencesource-ai-model-retirement-dates]
url = "https://referencesource.org/mcp/models"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "org-referencesource-ai-model-retirement-dates": {
      "type": "remote",
      "url": "https://referencesource.org/mcp/models",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add org-referencesource-ai-model-retirement-dates --url 'https://referencesource.org/mcp/models' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  org-referencesource-ai-model-retirement-dates:
    url: "https://referencesource.org/mcp/models"
```

### Netclaw

```json
{
  "McpServers": {
    "org-referencesource-ai-model-retirement-dates": {
      "Transport": "http",
      "Url": "https://referencesource.org/mcp/models"
    }
  }
}
```

### Vellum

```bash
assistant mcp add org-referencesource-ai-model-retirement-dates -t streamable-http -u 'https://referencesource.org/mcp/models'
```

### Other

```json
{
  "mcpServers": {
    "org-referencesource-ai-model-retirement-dates": {
      "type": "http",
      "url": "https://referencesource.org/mcp/models"
    }
  }
}
```

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.

### 2026-11-21 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 69, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-16 (score 69)

First indexed and scored.

## MCP tools (3)

### `model_status` (~317 tokens)

Is this AI model id retired, and when does it shut off?

Ask this before you pin, recommend or migrate off a model id. Give the id exactly as it goes in the config — "gpt-4o", "anthropic.claude-3-haiku-20240307-v1:0", "gemini-1.5-pro-002", "mistral-large-2407" — and get whether it is retired, the shutdown date the provider published, the replacement the provider names, and a verbatim quote of the page that says so. Where several hosts sell the same id you get every one of them, and earliest_announced_shutdown is the date a migration actually has to meet: on 34 records a second host switches the model off EARLIER than the record's primary source does. An id we hold nothing for returns found: false and no date, which means not in our records, never "still supported".

Input parameters:

- `model_id` (string, required): The model id as the provider writes it. Matched exactly, then case-insensitively, then against the alternative name a record's own id prints, then against the human-readable model name. Never as a su…
- `provider` (string): Optional. Narrow to one provider's schedule, matched case-insensitively as a substring of the provider name ("bedrock", "azure", "groq"). Leave it out to see every host's clock for this id, which is…

Output parameters:

- `answer` (string): One sentence, computed here from the records below, for a caller that needs a line rather than a structure.
- `as_of` (string): The UTC date every "has it passed" answer here was computed against.
- `coverage` (string)
- `earliest_announced_shutdown` (object): The soonest shutdown date any source states for this id, with the page and quote that state it. THE FIGURE TO PLAN AGAINST. Floors and no-date sentences are excluded; null where no source gives a dat…
- `found` (boolean)
- `matched_on` (string): Which rung of the ladder matched. Absent when nothing did.
- `model_id_asked` (string)
- `models` (array)
- `records_found` (integer)
- `register` (object)
- `similar_ids_in_our_records` (array): Only on a miss. Ids in this register containing the string you asked about. NOT AN ANSWER about any of them — no date and no status is attached, because you did not ask about them. Call model_status…

### `upcoming_retirements` (~251 tokens)

Which AI models shut off in the next N days?

What is about to break? Lists the model ids whose provider has published a shutdown date inside the next N days, soonest first, each with the provider, the replacement it names and a verbatim quote. Use it to sweep a codebase's pins before they bite, or to see what a quarter's migration work looks like. Optionally narrowed to one provider. Dates a provider printed as a floor ("not sooner than") are deliberately left out and counted in the response, because such a model could go years later and listing it here would be a guess.

Input parameters:

- `days` (integer): How far ahead to look, in days from today (UTC). 90 by default. Pass 0 to get only what is already past its date.
- `include_already_retired` (boolean): Include models whose shutdown date has already passed. False by default: this tool answers "what is coming". Set true to audit pins that are already dead.
- `limit` (integer): How many to return, 1–20. Default 20.
- `provider` (string): Optional case-insensitive substring of the provider name ("openai", "bedrock", "azure", "together").

Output parameters:

- `as_of` (string)
- `coverage` (string)
- `excluded_floor_dates` (integer): How many records fell in the window only on a date the provider printed as a floor ("not sooner than"), and were therefore left out. Reported so the omission is visible instead of silent.
- `from` (string)
- `models` (array)
- `models_matched` (integer)
- `models_returned` (integer)
- `register` (object)
- `to` (string)
- `window_days` (integer)

### `verify_quote` (~302 tokens)

Check a claimed model retirement date against the register

Is this right? Check a claim about a model id — its shutdown date, its lifecycle status, the replacement it was given — against the provider's own record instead of trusting it. Says whether the claim equals a stored value, appears only in the verbatim quote, or differs (and then what the record says instead). A model retirement date recalled from memory is exactly the kind of confident wrong answer that leaves a config pinned to something that stopped answering.

Input parameters:

- `claimed_value` (string, required): The value to check, exactly as claimed, e.g. "Terminated" or "2026-10-29".
- `field` (string): Which field the claim is about, if you know it. Without it, every stored field of the record is checked.
- `model_id` (string, required): The model id the claim is about, matched the same way model_status matches it. Where more than one record holds the id, narrow with `provider` or `record_id` — the check is refused rather than run ag…
- `provider` (string): Optional case-insensitive substring of the provider name, to pick which host's record the claim is checked against.
- `record_id` (string): Optional. The exact record to check against, as model_status returns it in record_id. Settles the case where one provider holds the same id twice (AWS Bedrock publishes two schedules for claude-3-hai…

Output parameters:

- `attestation` (string)
- `claimed_value` (string)
- `in_source_quote` (boolean)
- `match` (object)
- `quote_source` (string)
- `record` (object)
- `stored_values` (object)
- `verdict` (string): matches_record: the claim equals a stored value (match.match_type says how exactly). matches_quote: it appears in the verbatim source quote but is not a stored value. differs: the record was found an…

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/org-referencesource-ai-model-retirement-dates/mcp-models#diagnostics

## Score history

- 2026-11-21: 71
- 2026-11-20: 70
- 2026-11-19: 70
- 2026-11-18: 70
- 2026-11-17: 69
- 2026-11-16: 69

## Common questions

### What is the AI model deprecation and retirement dates, by provider MCP server?

AI model deprecation and retirement dates, by provider is an MCP server listed in the public MCP registry as org.referencesource/ai-model-retirement-dates. Is this AI model id retired, when does it shut off, and what does its provider say replaces it? This page covers its hosted endpoint (https://referencesource.org/mcp/models).

### Is the AI model deprecation and retirement dates, by provider MCP server safe to use?

AI model deprecation and retirement dates, by provider scores 71 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 AI model deprecation and retirement dates, by provider MCP server expose?

AI model deprecation and retirement dates, by provider exposes 3 tools: model_status, upcoming_retirements, verify_quote. Their descriptions and schemas cost roughly 870 tokens of context every time the server is loaded.

### Does the AI model deprecation and retirement dates, by provider MCP server require authentication?

No. We connected to AI model deprecation and retirement dates, by provider without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AI model deprecation and retirement dates, by provider MCP server still maintained?

AI model deprecation and retirement dates, by provider is still listed as active in the MCP registry. We last reached this channel on 21 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 AI model deprecation and retirement dates, by provider MCP server?

VerifyMCP ran 13 checks on AI model deprecation and retirement dates, by provider, 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://referencesource.org/mcp/models
- Website: https://referencesource.org/ai-model-deprecation-and-retirement
- Changelog RSS feed: https://verifymcp.io/servers/org-referencesource-ai-model-retirement-dates/mcp-models.xml
- Changelog JSON feed: https://verifymcp.io/servers/org-referencesource-ai-model-retirement-dates/mcp-models/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/org-referencesource-ai-model-retirement-dates/mcp-models.json
- HTML version of this page: https://verifymcp.io/servers/org-referencesource-ai-model-retirement-dates/mcp-models
