# AHG Archives (remote · mcp.theahg.co.za)

Search and read AtoM archival catalogues with citable links; staff propose changes for review.

- Trust score: 70/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `mcp.theahg.co.za`: 36/100, [markdown](https://verifymcp.io/servers/za-co-theahg-ahg-archives/mcp.md), [page](https://verifymcp.io/servers/za-co-theahg-ahg-archives/mcp)
- remote · `mcp.theahg.co.za`: 70/100 (this document), [markdown](https://verifymcp.io/servers/za-co-theahg-ahg-archives/public-mcp.md), [page](https://verifymcp.io/servers/za-co-theahg-ahg-archives/public-mcp)

## Channel facts

- Endpoint: `https://mcp.theahg.co.za/public/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.8.2`

## 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 2026-11-04.

- **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. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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**: 58/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2565 tokens (~160/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% 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 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the AHG Archives MCP server?

AHG Archives is a hosted endpoint at https://mcp.theahg.co.za/public/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 za-co-theahg-ahg-archives 'https://mcp.theahg.co.za/public/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "za-co-theahg-ahg-archives": {
      "url": "https://mcp.theahg.co.za/public/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "za-co-theahg-ahg-archives": {
      "type": "http",
      "url": "https://mcp.theahg.co.za/public/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.za-co-theahg-ahg-archives]
url = "https://mcp.theahg.co.za/public/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "za-co-theahg-ahg-archives": {
      "type": "remote",
      "url": "https://mcp.theahg.co.za/public/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add za-co-theahg-ahg-archives --url 'https://mcp.theahg.co.za/public/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  za-co-theahg-ahg-archives:
    url: "https://mcp.theahg.co.za/public/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "za-co-theahg-ahg-archives": {
      "Transport": "http",
      "Url": "https://mcp.theahg.co.za/public/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add za-co-theahg-ahg-archives -t streamable-http -u 'https://mcp.theahg.co.za/public/mcp'
```

### Other

```json
{
  "mcpServers": {
    "za-co-theahg-ahg-archives": {
      "type": "http",
      "url": "https://mcp.theahg.co.za/public/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.

### 2026-11-04 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 68, +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.

### 2026-10-29 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 66, +7)

- [security improvement] Authorization: unverified → partial

### 2026-10-27 (score 59, 0)

- [security] Tool “get_record_text” rewrote its description, which is the text the model reads
- [security] Tool “get_record_image” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 142 → 160
- [functional improvement] Stability: unverified → 0.03

### 2026-10-26 (score 59)

First indexed and scored.

## MCP tools (16)

### `search_records` (~137 tokens)

Search archival descriptions (fonds, series, files, items) by keyword.

    Returns title, level of description and the citable URL of each match.
    Use get_record on a result for the full description. catalogue: leave empty
    for the home catalogue, give a name from list_catalogues, or "all" to search
    every catalogue at once (results grouped by catalogue). Every read tool takes
    the same catalogue; read a result with the catalogue it came from.

Input parameters:

- `catalogue` (string)
- `limit` (integer)
- `query` (string, required)
- `skip` (integer)

### `list_catalogues` (~28 tokens)

The catalogues this service can search and read. Proposals go to the home catalogue only.

### `get_record` (~91 tokens)

Read one archival description in full, by its slug (the last part of its URL).

    Includes dates, names, subjects, places, notes and, where the catalogue
    provides them, its place in the hierarchy, its number of children, images,
    and its provenance chain (owners, dates, transfers, certainty, gaps).

Input parameters:

- `catalogue` (string)
- `slug` (string, required)

### `get_children` (~52 tokens)

List the descriptions directly below one record (for example the series in a fonds).

Input parameters:

- `catalogue` (string)
- `limit` (integer)
- `skip` (integer)
- `slug` (string, required)

### `work_through_series` (~197 tokens)

Work through every record below a parent (for example each page of a family
    Bible), a batch at a time, with a running summary of what you proposed where.

    Returns a batch of the parent's children, each with your proposals on it so
    far by status, the totals for the whole batch, how many proposals you may
    still make this hour, and next_skip for the next batch (null when done).
    For each child: read it (get_record, and get_record_text or get_record_image
    when its text is thin), skip it when your proposals there are still pending,
    propose, then move on. Call again with skip=next_skip until it is null. When
    get_record shows a child has children of its own, work through it the same way.

Input parameters:

- `limit` (integer)
- `skip` (integer)
- `slug` (string, required)

### `get_authority` (~39 tokens)

Read an authority record (a person, family or organisation) by its slug.

Input parameters:

- `catalogue` (string)
- `slug` (string, required)

### `search_authorities` (~142 tokens)

Find existing authority records (people, organisations, families) or places by name.

    Every word must appear in the name, in any order, so "Hendrik Engelbrecht"
    also finds "Engelbrecht, Hendrik". Use it before proposing a name or place:
    when one of the results is the same person, organisation or place, pass its
    id as existing_id in propose_access_points_and_dates, so the archivist links
    the existing record instead of creating a new one.

Input parameters:

- `catalogue` (string)
- `kind` (string)
- `limit` (integer)
- `name` (string, required)

### `get_iiif_manifest` (~45 tokens)

Return the IIIF manifest URL for a record's images, for viewing in a IIIF viewer.

Input parameters:

- `catalogue` (string)
- `slug` (string, required)

### `get_record_text` (~269 tokens)

Read the text held for a record's files: text extracted from a PDF or by OCR,
    and transcriptions of audio or video.

    Use it for documents, where reading the text beats looking at a small image.
    Long text comes in pages: if a result says more=true, call again with
    offset set to offset + the length you received. Personal information may be
    masked. Quote what you rely on when you propose changes. Where the catalogue states rights (OpenRiC Workspace, AtoM with the AHG Extensions, Heratio), each result carries
    rights: RightsStatements.org statements, Creative Commons licences, what may
    be done (PREMIS acts: allow, disallow, conditional) and Local Contexts labels.
    Follow them when you quote or reuse anything, and say what they are. A file
    whose labels ask for no reuse (TK Secret/Sacred, Community Use Only, Women or
    Men Restricted), or that may not be shown, is withheld: it is not given to
    you, and you should not try to describe or obtain it another way.

Input parameters:

- `catalogue` (string)
- `limit` (integer)
- `offset` (integer)
- `slug` (string, required)

### `get_record_image` (~253 tokens)

Look at a record's image: returns the reference image itself, so you can
    describe what it shows, read inscriptions or labels, or judge its condition.

    Use it before proposing a description for a record whose own text is thin.
    Only images the caller may view are returned (the reference copy, never the
    master). Say what you saw and what you inferred, and treat inscriptions you
    cannot read clearly as uncertain. Where the catalogue states rights (OpenRiC Workspace, AtoM with the AHG Extensions, Heratio), each result carries
    rights: RightsStatements.org statements, Creative Commons licences, what may
    be done (PREMIS acts: allow, disallow, conditional) and Local Contexts labels.
    Follow them when you quote or reuse anything, and say what they are. A file
    whose labels ask for no reuse (TK Secret/Sacred, Community Use Only, Women or
    Men Restricted), or that may not be shown, is withheld: it is not given to
    you, and you should not try to describe or obtain it another way.

Input parameters:

- `catalogue` (string)
- `slug` (string, required)

### `list_my_proposals` (~126 tokens)

List the proposals you made and what became of them, newest first.

    Each shows the record, the name, place, date or field text proposed, and its
    status: pending, approved, edited, linked (to an authority record), rejected,
    new_record_created or parked, with who reviewed it and when. Check it before
    proposing for a record, and do not propose again what was rejected. Needs the
    archivist's own staff key.

Input parameters:

- `limit` (integer)
- `skip` (integer)
- `status`

### `propose_access_points_and_dates` (~239 tokens)

Propose access points (people, organisations, places) and dates for one record.

    Read the record with get_record first. Propose only what its text, or a
    reliable source you name, supports; give the evidence and source URLs for
    each. For a person or organisation, also give dates_of_existence, a short
    history and places when the record or a source states them: they pre-fill
    the new authority record if the archivist creates one. Look names and places
    up with search_authorities first; when one is already in the catalogue, give
    its id as existing_id and why in link_reason, and the archivist sees it as
    the first candidate to link. Nothing on the record
    changes: an archivist reviews every proposal.
    On AtoM with the AHG extensions they are queued in AI > NER review; on stock
    AtoM they are returned for the archivist to apply. Needs the archivist's own
    staff key.

Input parameters:

- `proposals` (array, required)
- `slug` (string, required)

### `propose_relationships` (~134 tokens)

Propose relationships between people or organisations that a record states,
    such as a marriage or parent and child in a family register.

    Each side must be an existing authority record (give its id from
    search_authorities) or a person or organisation you have already proposed
    for this record with propose_access_points_and_dates. Give the line that
    states each relationship as evidence. An archivist reviews them in AI >
    Relationship review; approved ones show on both authority records. Needs
    the archivist's own staff key.

Input parameters:

- `relationships` (array, required)
- `slug` (string, required)

### `propose_description_change` (~191 tokens)

Propose new text for one field of a record, for an archivist to review.

    text is the complete proposed text for the field, not a fragment: read the
    record with get_record first and keep what is right in the current text.
    For a title, propose the title only (at most 1,024 characters).
    Give the evidence and the URLs of any web sources. Nothing on the record
    changes: on AtoM with the AHG extensions the proposal is queued in AI >
    Suggest review, where the archivist can edit it before approving; on stock
    AtoM it is returned for the archivist to apply. Needs the archivist's own
    staff key.

Input parameters:

- `evidence` (string)
- `field` (string, required)
- `slug` (string, required)
- `sources`
- `text` (string, required)

### `propose_transcription` (~187 tokens)

Propose a transcription of a record's file, such as a scanned page with no text.

    Look at the page with get_record_image first and transcribe what is written,
    line by line, in its own language and spelling; mark what you cannot read as
    [illegible] rather than guessing. Use get_record_text to see whether the file
    already has text. digital_object_id picks the file when a record has several.
    At most 65,000 bytes: propose a long document page by page. An archivist
    compares it with the page image in AI > Suggest review; once approved it is
    the file's text and is searchable. Needs the archivist's own staff key.

Input parameters:

- `digital_object_id`
- `evidence` (string)
- `slug` (string, required)
- `text` (string, required)

### `propose_translation` (~155 tokens)

Propose a translation of one field of a record into another language.

    language is the target language code, e.g. "en", "af" or "nl". Translate the
    record's current text for that field faithfully (read it with get_record);
    keep names, dates and reference codes as they are. An archivist reviews it in
    AI > Suggest review next to any text already held in that language; once
    approved the record shows it in that language. Needs the archivist's own
    staff key.

Input parameters:

- `evidence` (string)
- `field` (string, required)
- `language` (string, required)
- `slug` (string, required)
- `text` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/za-co-theahg-ahg-archives/public-mcp#diagnostics

## Score history

- 2026-11-04: 70
- 2026-11-03: 69
- 2026-11-02: 69
- 2026-11-01: 68
- 2026-10-31: 68
- 2026-10-30: 67
- 2026-10-29: 67
- 2026-10-28: 66
- 2026-10-27: 59
- 2026-10-26: 59

## Common questions

### What is the AHG Archives MCP server?

AHG Archives is an MCP server listed in the public MCP registry as za.co.theahg/ahg-archives. Search and read AtoM archival catalogues with citable links; staff propose changes for review. This page covers its hosted endpoint (https://mcp.theahg.co.za/public/mcp).

### Is the AHG Archives MCP server safe to use?

AHG Archives scores 70 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 AHG Archives MCP server expose?

AHG Archives exposes 16 tools: search_records, list_catalogues, get_record, get_children, work_through_series, and 11 more. Their descriptions and schemas cost roughly 2,285 tokens of context every time the server is loaded.

### Does the AHG Archives MCP server require authentication?

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

### Is the AHG Archives MCP server still maintained?

AHG Archives is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.theahg.co.za/public/mcp
- Repository: https://github.com/ArchiveHeritageGroup/ahg-archives-mcp
- Website: https://www.atom-extensions.com/
- Changelog RSS feed: https://verifymcp.io/servers/za-co-theahg-ahg-archives/public-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/za-co-theahg-ahg-archives/public-mcp.json
- HTML version of this page: https://verifymcp.io/servers/za-co-theahg-ahg-archives/public-mcp