
SWAPI MCP server
Which MCP servers are SWAPI's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-11-03
- Registry namebuild.swapi/star-warsverified in the MCP registry
The registry name sits under swapi.build. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-11-03
- Tools4
- Server calls itselfswapi.build
- Server version2.15.0
- Protocol version2025-06-18
On 2026-11-03 the server answered initialize and tools/list without a sign-in. First answer in 540 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Once connected
- For "query people, planets, films and starships over REST", the likely first call is sw_search.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- Use4 GitHub stars
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer595 ms
- Space in an agent's context≈ 970 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- can do · query people, planets, films and starships over REST
- not sure · connect AI agents to Star Wars data via MCP
- not sure · explore the API interactively in a browser terminal
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
sw_getGets one Star Wars entity by numeric record id and returns it as a JSON object. Take the id from the end of an entity's url field (from sw_search, sw_list or a relation URL). Ids are record ids, not episode numbers: FILMS id 1 is A New…
sw_listLists every entity of one Star Wars resource type as a JSON array (Episodes I-VI data). Responses are large (all 82 PEOPLE, about 38 KB); to find a single entity, prefer sw_search, then sw_get; for a compact index pass fields, e.g…
sw_randomReturns one random Star Wars entity of the given resource type as a JSON object. Each call can return a different entity, so it is not idempotent. Useful for demos and quizzes; to fetch a specific entity use sw_search or sw_get.
sw_searchStart here. Finds Star Wars entities by name (title for FILMS) with a case-insensitive substring match: 'sky' finds Luke, Anakin and Shmi Skywalker. Returns a JSON array of full entities; an empty array [] means no match; pass fields to…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"star-wars": {
"type": "http",
"url": "https://swapi.build/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http swapi https://swapi.build/mcpclaude.ai, ChatGPT and other clients: add https://swapi.build/mcp as a custom connector in the settings.
OpenAPI spec
20 paths, read 2026-11-03. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.