coilyco-flight-deck/eco-mcp-app
1
0
Fork 0
Code Issues 18 Pull requests Projects Releases Packages Wiki Activity Actions 2

Wikidata Ecopedia #10

New issue
Open
opened 2026-05-23 20:54:11 +00:00 by coilysiren · 0 comments
coilysiren commented 2026-05-23 20:54:11 +00:00
Owner
Copy link

Originally filed by @coilysiren on 2026-05-02T23:10:02Z - https://github.com/coilysiren/eco-mcp-app/issues/15

Task 6 — Wikidata Ecopedia

Prereq: read todo/README.md first.

Goal

Build an MCP tool explain_eco_item(name, category?) rendering a card about any Eco item using Wikidata + Wikipedia.

Flow

  1. category is optional; it disambiguates the SPARQL query. Example: name="Iron", category="material" filters to Q677 (chemical element) rather than mythological figures named Iron.
  2. Query https://query.wikidata.org/sparql for the item's Wikidata entity; extract:
    • image (P18)
    • short description
    • category-specific facts (P-codes vary):
      • material (elements): atomic number P1086
      • plant: taxon rank P105
      • animal: taxon rank P105, conservation status P141
      • mineral: Mohs hardness P1088
      • food: main food source P186
  3. Fallback: GET https://en.wikipedia.org/api/rest_v1/page/summary/{name} for a short text summary when SPARQL yields nothing usable.
  4. Render a card: image, 2-line description, a facts table.

Required request headers (both Wikidata and Wikipedia)

User-Agent: eco-mcp-app/0.1 (coilysiren@gmail.com)
Accept: application/sparql-results+json    # Wikidata
Accept: application/json                    # Wikipedia

Caching

  • SQLite at ~/.cache/eco-mcp-app/wikidata.sqlite.
  • 7-day TTL on all external responses.
  • Wikidata SPARQL endpoint rate-limits aggressively (commonly 60 req/min per IP); never call without caching.

Default category

If no category provided: try Wikipedia REST /page/summary/{name} first (cheap, always returns something or 404). Only hit SPARQL when that fails or returns an ambiguous disambiguation page.

Categories to support

  • material
  • plant
  • animal
  • mineral
  • food

Implementation notes

  • Inline the image as a data: URI (CSP).
  • Add MCP tool to src/eco_mcp_app/server.py.
  • Template under src/eco_mcp_app/templates/partials/.

Acceptance

  • Tool works on ["Iron", "Oak", "Bison", "Wheat", "Quartz"] and returns a card with image + description + facts for each.
  • Second call for any of those is served from SQLite (check ~/.cache/eco-mcp-app/wikidata.sqlite exists and contains rows).
  • inv smoke passes.
_Originally filed by @coilysiren on 2026-05-02T23:10:02Z - [https://github.com/coilysiren/eco-mcp-app/issues/15](https://github.com/coilysiren/eco-mcp-app/issues/15)_ # Task 6 — Wikidata Ecopedia **Prereq**: read `todo/README.md` first. ## Goal Build an MCP tool `explain_eco_item(name, category?)` rendering a card about any Eco item using Wikidata + Wikipedia. ## Flow 1. `category` is optional; it disambiguates the SPARQL query. Example: `name="Iron"`, `category="material"` filters to Q677 (chemical element) rather than mythological figures named Iron. 2. Query `https://query.wikidata.org/sparql` for the item's Wikidata entity; extract: - image (P18) - short description - category-specific facts (P-codes vary): - `material` (elements): atomic number P1086 - `plant`: taxon rank P105 - `animal`: taxon rank P105, conservation status P141 - `mineral`: Mohs hardness P1088 - `food`: main food source P186 3. Fallback: `GET https://en.wikipedia.org/api/rest_v1/page/summary/{name}` for a short text summary when SPARQL yields nothing usable. 4. Render a card: image, 2-line description, a facts table. ## Required request headers (both Wikidata and Wikipedia) ``` User-Agent: eco-mcp-app/0.1 (coilysiren@gmail.com) Accept: application/sparql-results+json # Wikidata Accept: application/json # Wikipedia ``` ## Caching - SQLite at `~/.cache/eco-mcp-app/wikidata.sqlite`. - 7-day TTL on all external responses. - Wikidata SPARQL endpoint rate-limits aggressively (commonly 60 req/min per IP); **never call without caching**. ## Default category If no `category` provided: try Wikipedia REST `/page/summary/{name}` first (cheap, always returns something or 404). Only hit SPARQL when that fails or returns an ambiguous disambiguation page. ## Categories to support - `material` - `plant` - `animal` - `mineral` - `food` ## Implementation notes - Inline the image as a `data:` URI (CSP). - Add MCP tool to `src/eco_mcp_app/server.py`. - Template under `src/eco_mcp_app/templates/partials/`. ## Acceptance - Tool works on `["Iron", "Oak", "Bison", "Wheat", "Quartz"]` and returns a card with image + description + facts for each. - Second call for any of those is served from SQLite (check `~/.cache/eco-mcp-app/wikidata.sqlite` exists and contains rows). - `inv smoke` passes.
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
claude/climate-parallel-arrays
No results found.
Labels
Clear labels
  
P0
now / blocking / urgent

  
P1
next / important

  
P2
backlog / will do

  
P3
someday / low

  
P4
icebox / frozen / reopen if it becomes real

No labels
P0
P1
P2
P3
P4
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
coilyco-flight-deck/eco-mcp-app#10
No description provided.