GraphQL MCP

 

Why not just return the whole GraphQL schema?

Swan's GraphQL schema is 200 000+ characters long (it's HUGE)

  • It's over the context limit of most LLMs
  • It would waste many tokens with irrelevant parts of the schema
  • Longer context = lower accuracy

How it works

The server runs a standard introspection query against our GraphQL endpoint.

Step 1: Introspection

Step 2: Indexing

Step 2: Indexing

type Query {
  user: User
  account: Account
}
type User {
  account: Account
}
type Account {
  iban: String
}

Query

User

Account

String

user

account

account

iban

Step 2: Indexing

To prepare for the indexing, we traverse the graph (BFS - Breadth-First Search) and for each field, we:

  • assign a score based on its depth
  • store its:
    • path
    • description
    • parent type
    • type
    • the description of its type

... and put everything in FlexSearch, an in-memory full-text search engine

For Account.iban, we index: iban, account, string, plus its description.

Step 2: Indexing

Query

User

Account

String

user

account

account

iban

Depth 1:

  • user (Query, User)
  • account (Query, Account)

Depth 2:

  • user.account (User, Account)
  • account.iban (Account, String)

Depth 3:

  • user.account.iban (Account, String)

Step 3: Scoring

Step 3: Scoring

When the AI searches for ["IBAN"], FlexSearch returns all matching fields.

 

 

We then rank them:

 

 

score = (3*name + 2*description + parent_type)/depth

 

  • Walk up to Query/Mutation to include all intermediaries
  • Rince and repeat until we hit a size limit (configurable by the agent, with a default to 10000 characters)

Final touch:

Docs MCP

Semantic Search 

Step 1: Scraping https://docs.swan.io (sitemap.xml)

Step 2: Chunking

  • by html section
  • recursing splitting

Step 3: Embedding (vectorization)

  • Qdrant database
  • index all words of each chunk, keep link to original doc url and content
  • index rebuilt every 6 hours

Step 4: Semantic search

  • vector distance, handled by Qdrant

Semantic Search 

Thank you

Made with Slides.com