UK National Archives Discovery
PYPI · TNA-DISCOVERY-MCP
Search the UK National Archives' Discovery catalogue; find Chelsea pensioners' papers in WO 97.
Available components
Last scanned (14 hours ago)
Scores higher than 79% of PyPI servers
Category Education and Research
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 32 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to ianderso/tna-discovery-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 6 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability61
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1198 tokens (~239/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 14 Oct 26 +29
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Schema quality: good functional
- First check of Tool coverage: 100 functional
- 13 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 12 Oct 26 35
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 18 Oct 2026 · Analysed pypi/tna-discovery-mcp@0.1.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | ianderso/tna-discovery-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/ianderso/tna-discovery-mcp/.github/workflows/release.yml@refs/tags/v0.1.0 |
| Rekor log index | 3200908749 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:173cf93da09cc4187360f0b040c0bfd095137151b13728c496ee6bed153cbc0f |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 32 packages
| Packages resolved | 32 |
|---|---|
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
browse ~181
List the records one level below a series, sub-series or piece, in catalogue order. Walks down department, series, sub-series, piece, item. WO 97's pieces to 1854 each hold one regiment's men, alphabetically; WO 12 lists regiments, then a piece per year. For one regiment in one year, search_records with `series` is quicker. No children means a piece or item with nothing described below it, or an unknown id.
| Name | Type | Req | Description |
|---|---|---|---|
| after | string | – | To continue, the `next_after` value of the previous answer. |
| limit | integer | – | Children to return (1-200). |
| reference_or_id | string | yes | A series, sub-series or piece: a reference such as 'WO 12' or 'WO 97/1211', or a record id. |
No output schema declared.
No examples provided.
budget_status ~25
Report today's requests against the daily budget, and the last error. No network call.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
find_soldier ~245
Find a soldier's discharge papers in WO 97 (Chelsea pensioners, 1760-1854), parsed. Searches the name in WO 97 and keeps the men whose names, discharge year, regiment and birthplace fit, each with his TNA reference, regiments, birthplace, discharge age and an estimated birth year. Only men discharged to a pension are here. Spellings vary (HARGRAVES alias HARGREAVES): try variants and a trailing *. Same name is not same man.
| Name | Type | Req | Description |
|---|---|---|---|
| birthplace | string | – | Words of the birthplace or county, e.g. 'Lancashire'. |
| discharged_from | – | – | Earliest discharge year. |
| discharged_to | – | – | Latest discharge year. |
| forename | string | – | Forename(s), e.g. 'John'. |
| page | integer | – | Page of the name search, 500 descriptions each. |
| regiment | string | – | Words of a regiment, e.g. '33rd Foot'; matched loosely. |
| surname | string | yes | Surname, e.g. 'Atkinson'. A trailing * matches spellings that begin so: 'Hargr*'. |
No output schema declared.
No examples provided.
get_record ~183
Read one catalogue description in full, with its hierarchy and how to cite it. A reference must be exact and costs one more request than an id. For a WO 97 item (soldiers' discharge papers, 1760-1854) `soldier` parses the description into name, birthplace, county, regiments, discharge age and year, service years and an estimated birth year, keeping `original`. `images` says where the record itself can be read: this is a finding aid.
| Name | Type | Req | Description |
|---|---|---|---|
| hierarchy | boolean | – | Also read where the record sits: department, series, piece. One request. |
| id_or_reference | string | yes | A record id from a search, e.g. 'C8853102', or a catalogue reference, e.g. 'WO 97/1211/256' or 'WO 12'. |
No output schema declared.
No examples provided.
search_records ~336
Search Discovery's catalogue descriptions: TNA's records and 2,500 other archives'. Dates select records whose covering dates overlap the range. Each hit has its id (for get_record), reference, description, covering dates, holding archive, `digitised` (TNA holds an image) and the record's page. A WO 97 item also carries `soldier`, its description parsed. Hits are finding aids, not records; a zero covers only what was searched.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | Hits per page (1-100). |
| date_from | string | – | Covering dates from: '1831' or '1831-06-15'. |
| date_to | string | – | Covering dates to: '1834' or '1834-12-31'. |
| department | string | – | A TNA department code, e.g. 'WO' or 'HO'. |
| held_by | string | – | 'tna' for TNA's own records, 'other' for other archives', or an Archon code such as '182'. Default all. |
| page | integer | – | Page of results, 1-based. |
| query | string | – | Words to find in descriptions, e.g. 'atkinson manchester'. All words must match; OR, NOT, "phrases" and a trailing * work. |
| series | string | – | A series code, e.g. 'WO 97' or 'PROB 11'. |
| sort | string | – | Order. Relevance ties shuffle between pages; page with 'reference' or 'date'. |
No output schema declared.
No examples provided.
How do I install the UK National Archives Discovery MCP server?
UK National Archives Discovery runs locally as a PyPI package, launched with uvx tna-discovery-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · tna-discovery-mcp
claude mcp add ianderso-tna-discovery-mcp -- uvx tna-discovery-mcp
What is the UK National Archives Discovery MCP server?
UK National Archives Discovery is an MCP server listed in the public MCP registry as io.github.ianderso/tna-discovery-mcp. Search the UK National Archives' Discovery catalogue; find Chelsea pensioners' papers in WO 97. This page covers its PyPI package (tna-discovery-mcp).
Is the UK National Archives Discovery MCP server safe to use?
UK National Archives Discovery scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. Its build provenance is signed and verified. 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 UK National Archives Discovery MCP server expose?
UK National Archives Discovery exposes 5 tools: search_records, get_record, browse, find_soldier, budget_status. Their descriptions and schemas cost roughly 970 tokens of context every time the server is loaded.
Is the UK National Archives Discovery MCP server still maintained?
UK National Archives Discovery is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the UK National Archives Discovery MCP server under?
UK National Archives Discovery declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.