@mastra/mcp-docs-server 1.1.8 → 1.1.9-alpha.1

package/.docs/reference/tools/mcp-client.md

@@ -22,7 +22,7 @@ constructor({
 
 **timeout** (`number`): Global timeout value in milliseconds for all servers unless overridden in individual server configs. (Default: `60000`)
 
-### MastraMCPServerDefinition
+### `MastraMCPServerDefinition`
 
 Each server in the `servers` map is configured using the `MastraMCPServerDefinition` type. The transport type is detected based on the provided parameters:
 
@@ -55,7 +55,7 @@ Each server in the `servers` map is configured using the `MastraMCPServerDefinit
 
 ## Methods
 
-### listTools()
+### `listTools()`
 
 Retrieves all tools from all configured servers, with tool names namespaced by their server name (in the format `serverName_toolName`) to prevent conflicts. Intended to be passed onto an Agent definition.
 
@@ -63,7 +63,7 @@ Retrieves all tools from all configured servers, with tool names namespaced by t
 new Agent({ id: 'agent', tools: await mcp.listTools() })
 ```
 
-### listToolsets()
+### `listToolsets()`
 
 Returns an object mapping namespaced tool names (in the format `serverName.toolName`) to their tool implementations. Intended to be passed dynamically into the generate or stream method.
 
@@ -73,7 +73,7 @@ const res = await agent.stream(prompt, {
 })
 ```
 
-### disconnect()
+### `disconnect()`
 
 Disconnects from all MCP servers and cleans up resources.
 
@@ -239,7 +239,7 @@ mcpClient.elicitation.onRequest('serverName', async request => {
 
 Sets up a handler function that will be called when any connected MCP server sends an elicitation request. The handler receives the request and must return a response.
 
-##### ElicitationHandler Function
+##### `ElicitationHandler` Function
 
 The handler function receives a request object with:
 
@@ -534,7 +534,7 @@ mcpClient.elicitation.onRequest('interactiveServer', async request => {
 })
 ```
 
-### Response Types
+### Response types
 
 Your elicitation handler must return one of three response types:
 
@@ -592,7 +592,7 @@ await mcpClient.elicitation.onRequest('interactiveServer', async request => {
 })
 ```
 
-### Best Practices
+### Best practices
 
 - **Always handle elicitation**: Set up your handler before calling tools that might use elicitation
 - **Validate input**: Check that required fields are provided
@@ -600,7 +600,7 @@ await mcpClient.elicitation.onRequest('interactiveServer', async request => {
 - **Clear UI**: Make it obvious what information is being requested and why
 - **Security**: Never auto-accept requests for sensitive information
 
-## OAuth Authentication
+## OAuth authentication
 
 For connecting to MCP servers that require OAuth authentication per the [MCP Auth Specification](https://modelcontextprotocol.io/specification/2025-06-18/basic/authorization), use the `MCPOAuthClientProvider`:
 
@@ -819,7 +819,7 @@ const response = await agent.stream('How is AAPL doing and what is the weather?'
 })
 ```
 
-## Instance Management
+## Instance management
 
 The `MCPClient` class includes built-in memory leak prevention for managing multiple instances:
 
@@ -863,7 +863,7 @@ const mcp4 = new MCPClient({
 })
 ```
 
-## Server Lifecycle
+## Server lifecycle
 
 MCPClient handles server connections gracefully:
 
@@ -871,7 +871,7 @@ MCPClient handles server connections gracefully:
 2. Graceful server shutdown to prevent error messages during development
 3. Proper cleanup of resources when disconnecting
 
-## Using Custom Fetch for Dynamic Authentication
+## Using custom fetch for dynamic authentication
 
 For HTTP servers, you can provide a custom `fetch` function to handle dynamic authentication, request interception, or other custom behavior. This is particularly useful when you need to refresh tokens on each request or forward user credentials from the incoming request to the MCP server.
 
@@ -910,7 +910,7 @@ await agent.generate('Hello!', {
 })
 ```
 
-## Using SSE Request Headers
+## Using SSE request headers
 
 When using the legacy SSE MCP transport, you must configure both `requestInit` and `eventSourceInit` due to a bug in the MCP SDK. Alternatively, you can use a custom `fetch` function which will be automatically used for both POST requests and SSE connections:
 
@@ -959,7 +959,7 @@ const sseClientWithFetch = new MCPClient({
 })
 ```
 
-## Related Information
+## Related information
 
 - For creating MCP servers, see the [MCPServer documentation](https://mastra.ai/reference/tools/mcp-server).
 - For more about the Model Context Protocol, see the [@modelcontextprotocol/sdk documentation](https://github.com/modelcontextprotocol/typescript-sdk).

package/.docs/reference/tools/mcp-server.md

@@ -83,7 +83,7 @@ The constructor accepts an `MCPServerConfig` object with the following propertie
 
 **prompts** (`MCPServerPrompts`): An object defining how the server should handle MCP prompts. See Prompt Handling section for details.
 
-## Exposing Agents as Tools
+## Exposing agents as tools
 
 A powerful feature of `MCPServer` is its ability to automatically expose your Mastra Agents as callable tools. When you provide agents in the `agents` property of the configuration:
 
@@ -96,9 +96,9 @@ A powerful feature of `MCPServer` is its ability to automatically expose your Ma
   - **Execution**: When this tool is called, it invokes the `generate()` method of the corresponding agent, passing the provided `query`.
   - **Output**: The direct result from the agent's `generate()` method is returned as the output of the tool.
 
-- **Name Collisions**: If an explicit tool defined in the `tools` configuration has the same name as an agent-derived tool (e.g., you have a tool named `ask_myAgentKey` and also an agent with the key `myAgentKey`), the _explicitly defined tool will take precedence_. The agent will not be converted into a tool in this conflicting case, and a warning will be logged.
+- **Name Collisions**: If an explicit tool defined in the `tools` configuration has the same name as an agent-derived tool (e.g., you have a tool named `ask_myAgentKey` and also an agent with the key `myAgentKey`), the _explicitly defined tool will take precedence_. The agent won't be converted into a tool in this conflicting case, and a warning will be logged.
 
-This makes it straightforward to allow MCP clients to interact with your agents using natural language queries, just like any other tool.
+This makes it straightforward to allow MCP clients to interact with your agents using natural language queries, like any other tool.
 
 ### Agent-to-Tool Conversion
 
@@ -164,7 +164,7 @@ const fetchUserData = createTool({
 
 These are the functions you can call on an `MCPServer` instance to control its behavior and get information.
 
-### startStdio()
+### `startStdio()`
 
 Use this method to start the server so it communicates using standard input and output (stdio). This is typical when running the server as a command-line program.
 
@@ -186,7 +186,7 @@ const server = new MCPServer({
 await server.startStdio()
 ```
 
-### startSSE()
+### `startSSE()`
 
 This method helps you integrate the MCP server with an existing web server to use Server-Sent Events (SSE) for communication. You'll call this from your web server's code when it receives a request for the SSE or message paths.
 
@@ -238,7 +238,7 @@ Here are the details for the values needed by the `startSSE` method:
 
 **res** (`any`): The response object from your web server, used to send data back.
 
-### startHonoSSE()
+### `startHonoSSE()`
 
 This method helps you integrate the MCP server with an existing web server to use Server-Sent Events (SSE) for communication. You'll call this from your web server's code when it receives a request for the SSE or message paths.
 
@@ -290,7 +290,7 @@ Here are the details for the values needed by the `startHonoSSE` method:
 
 **res** (`any`): The response object from your web server, used to send data back.
 
-### startHTTP()
+### `startHTTP()`
 
 This method helps you integrate the MCP server with an existing web server to use streamable HTTP for communication. You'll call this from your web server's code when it receives HTTP requests.
 
@@ -391,7 +391,7 @@ serve(async req => {
 >
 > The serverless mode disables session management and creates fresh server instances per request, which is necessary for stateless environments where memory doesn't persist between invocations.
 >
-> **Note:** The following MCP features require session state or persistent connections and will **not work** in serverless mode:
+> **Note:** The following MCP features require session state or persistent connections and **won't work** in serverless mode:
 >
 > - **Elicitation** - Interactive user input requests during tool execution require session management to route responses back to the correct client
 > - **Resource subscriptions** - `resources/subscribe` and `resources/unsubscribe` need persistent connections to maintain subscription state
@@ -424,7 +424,7 @@ The `StreamableHTTPServerTransportOptions` object allows you to customize the be
 
 **eventStore** (`EventStore`): An event store for message resumability. Providing this enables clients to reconnect and resume message streams.
 
-### close()
+### `close()`
 
 This method closes the server and releases all resources.
 
@@ -432,7 +432,7 @@ This method closes the server and releases all resources.
 async close(): Promise<void>
 ```
 
-### getServerInfo()
+### `getServerInfo()`
 
 This method gives you a look at the server's basic information.
 
@@ -440,7 +440,7 @@ This method gives you a look at the server's basic information.
 getServerInfo(): ServerInfo
 ```
 
-### getServerDetail()
+### `getServerDetail()`
 
 This method gives you a detailed look at the server's information.
 
@@ -448,7 +448,7 @@ This method gives you a detailed look at the server's information.
 getServerDetail(): ServerDetail
 ```
 
-### getToolListInfo()
+### `getToolListInfo()`
 
 This method gives you a look at the tools that were set up when you created the server. It's a read-only list, useful for debugging purposes.
 
@@ -456,7 +456,7 @@ This method gives you a look at the tools that were set up when you created the
 getToolListInfo(): ToolListInfo
 ```
 
-### getToolInfo()
+### `getToolInfo()`
 
 This method gives you detailed information about a specific tool.
 
@@ -464,7 +464,7 @@ This method gives you detailed information about a specific tool.
 getToolInfo(toolName: string): ToolInfo
 ```
 
-### executeTool()
+### `executeTool()`
 
 This method executes a specific tool and returns the result.
 
@@ -472,7 +472,7 @@ This method executes a specific tool and returns the result.
 executeTool(toolName: string, input: any): Promise<any>
 ```
 
-### getStdioTransport()
+### `getStdioTransport()`
 
 If you started the server with `startStdio()`, you can use this to get the object that manages the stdio communication. This is mostly for checking things internally or for testing.
 
@@ -480,7 +480,7 @@ If you started the server with `startStdio()`, you can use this to get the objec
 getStdioTransport(): StdioServerTransport | undefined
 ```
 
-### getSseTransport()
+### `getSseTransport()`
 
 If you started the server with `startSSE()`, you can use this to get the object that manages the SSE communication. Like `getStdioTransport`, this is mainly for internal checks or testing.
 
@@ -488,7 +488,7 @@ If you started the server with `startSSE()`, you can use this to get the object
 getSseTransport(): SSEServerTransport | undefined
 ```
 
-### getSseHonoTransport()
+### `getSseHonoTransport()`
 
 If you started the server with `startHonoSSE()`, you can use this to get the object that manages the SSE communication. Like `getSseTransport`, this is mainly for internal checks or testing.
 
@@ -496,7 +496,7 @@ If you started the server with `startHonoSSE()`, you can use this to get the obj
 getSseHonoTransport(): SSETransport | undefined
 ```
 
-### getStreamableHTTPTransport()
+### `getStreamableHTTPTransport()`
 
 If you started the server with `startHTTP()`, you can use this to get the object that manages the HTTP communication. Like `getSseTransport`, this is mainly for internal checks or testing.
 
@@ -504,7 +504,7 @@ If you started the server with `startHTTP()`, you can use this to get the object
 getStreamableHTTPTransport(): StreamableHTTPServerTransport | undefined
 ```
 
-### tools()
+### `tools()`
 
 Executes a specific tool provided by this MCP server.
 
@@ -522,7 +522,7 @@ async executeTool(
 
 **executionContext** (`object`): Optional context for the tool execution, like messages or a toolCallId.
 
-## Resource Handling
+## Resource handling
 
 ### What are MCP Resources?
 
@@ -649,7 +649,7 @@ Example:
 await serverWithResources.resources.notifyListChanged()
 ```
 
-## Prompt Handling
+## Prompt handling
 
 ### What are MCP Prompts?
 
@@ -758,7 +758,7 @@ Call this method when the overall list of available prompts has changed (e.g., a
 await serverWithPrompts.prompts.notifyListChanged()
 ```
 
-### Best Practices for Prompt Handling
+### Best practices for Prompt Handling
 
 - Use clear, descriptive prompt names and descriptions.
 - Validate all required arguments in `getPromptMessages`.
@@ -778,7 +778,7 @@ The example at the beginning of this page also demonstrates how to instantiate `
 
 ## Elicitation
 
-### What is Elicitation?
+### What's Elicitation?
 
 Elicitation is a feature in the Model Context Protocol (MCP) that allows servers to request structured information from users. This enables interactive workflows where servers can collect additional data dynamically.
 
@@ -982,7 +982,7 @@ type ElicitResult = {
 }
 ```
 
-## OAuth Protection
+## OAuth protection
 
 To protect your MCP server with OAuth authentication per the [MCP Auth Specification](https://modelcontextprotocol.io/specification/2025-06-18/basic/authorization), use the `createOAuthMiddleware` function:
 
@@ -1085,11 +1085,11 @@ const customMiddleware = createOAuthMiddleware({
 
 **mcpPath** (`string`): Path where the MCP endpoint is served. Only requests to this path require authentication. (Default: `'/mcp'`)
 
-## Authentication Context
+## Authentication context
 
 Tools can access request metadata via `context.mcp.extra` when using HTTP-based transports. This allows you to pass authentication info, user context, or any custom data from your HTTP middleware to your MCP tools.
 
-### How It Works
+### How it works
 
 Whatever you set on `req.auth` in your HTTP middleware becomes available as `context.mcp.extra.authInfo` in your tools:
 
@@ -1265,7 +1265,7 @@ app.all('/mcp', async (req, res) => {
 app.listen(3000)
 ```
 
-## Related Information
+## Related information
 
 - For connecting to MCP servers in Mastra, see the [MCPClient documentation](https://mastra.ai/reference/tools/mcp-client).
 - For more about the Model Context Protocol, see the [@modelcontextprotocol/sdk documentation](https://github.com/modelcontextprotocol/typescript-sdk).

package/.docs/reference/tools/vector-query-tool.md

@@ -2,7 +2,7 @@
 
 The `createVectorQueryTool()` function creates a tool for semantic search over vector stores. It supports filtering, reranking, database-specific configurations, and integrates with various vector store backends.
 
-## Basic Usage
+## Basic usage
 
 ```typescript
 import { createVectorQueryTool } from '@mastra/rag'
@@ -79,7 +79,7 @@ The tool returns an object with:
 
 **sources** (`QueryResult[]`): Array of full retrieval result objects. Each object contains all information needed to reference the original document, chunk, and similarity score.
 
-### QueryResult object structure
+### `QueryResult` object structure
 
 ```typescript
 {
@@ -91,7 +91,7 @@ The tool returns an object with:
 }
 ```
 
-## Default Tool Description
+## Default tool description
 
 The default description focuses on:
 
@@ -99,11 +99,11 @@ The default description focuses on:
 - Answering user questions
 - Retrieving factual content
 
-## Result Handling
+## Result handling
 
 The tool determines the number of results to return based on the user's query, with a default of 10 results. This can be adjusted based on the query requirements.
 
-## Example with Filters
+## Example with filters
 
 ```typescript
 const queryTool = createVectorQueryTool({
@@ -134,7 +134,7 @@ For detailed filter syntax and store-specific capabilities, see the [Metadata Fi
 
 For an example of how agent-driven filtering works, see the [Agent-Driven Metadata Filtering](https://github.com/mastra-ai/mastra/tree/main/examples/basics/rag/filter-rag) example.
 
-## Example with Reranking
+## Example with reranking
 
 ```typescript
 const queryTool = createVectorQueryTool({
@@ -164,7 +164,7 @@ Reranking improves result quality by combining:
 
 The reranker processes the initial vector search results and returns a reordered list optimized for relevance.
 
-## Example with Custom Description
+## Example with custom description
 
 ```typescript
 const queryTool = createVectorQueryTool({
@@ -178,7 +178,7 @@ const queryTool = createVectorQueryTool({
 
 This example shows how to customize the tool description for a specific use case while maintaining its core purpose of information retrieval.
 
-## Database-Specific Configuration Examples
+## Database-specific configuration examples
 
 The `databaseConfig` parameter allows you to leverage unique features and optimizations specific to each vector database. These configurations are automatically applied during query execution.
 
@@ -335,7 +335,7 @@ This approach allows you to:
 - Adjust performance parameters based on load
 - Apply different filtering strategies per request
 
-## Example: Using Request Context
+## Example: Using request context
 
 ```typescript
 const queryTool = createVectorQueryTool({
@@ -374,7 +374,7 @@ For more information on request context, please see:
 - [Agent Request Context](https://mastra.ai/docs/server/request-context)
 - [Request Context](https://mastra.ai/docs/server/request-context)
 
-## Usage Without a Mastra Server
+## Usage without a Mastra server
 
 The tool can be used by itself to retrieve documents matching a query:
 
@@ -401,7 +401,7 @@ const queryResult = await vectorQueryTool.execute({ queryText: 'foo', topK: 1 },
 console.log(queryResult.sources)
 ```
 
-## Dynamic Vector Store for Multi-Tenant Applications
+## Dynamic vector store for multi-tenant applications
 
 For multi-tenant applications where each tenant has isolated data (e.g., separate PostgreSQL schemas), you can pass a resolver function instead of a static vector store instance. The function receives the request context and can return the appropriate vector store for the current tenant:
 
@@ -457,7 +457,7 @@ This pattern is similar to how `Agent.memory` supports dynamic configuration and
 - **Database isolation**: Route to different database instances per tenant
 - **Dynamic configuration**: Adjust vector store settings based on request context
 
-## Tool Details
+## Tool details
 
 The tool is created with:
 

package/.docs/reference/vectors/astra.md

@@ -1,8 +1,8 @@
-# Astra Vector Store
+# Astra vector store
 
 The AstraVector class provides vector search using [DataStax Astra DB](https://www.datastax.com/products/datastax-astra), a cloud-native, serverless database built on Apache Cassandra. It provides vector search capabilities with enterprise-grade scalability and high availability.
 
-## Constructor Options
+## Constructor options
 
 **token** (`string`): Astra DB API token
 
@@ -12,7 +12,7 @@ The AstraVector class provides vector search using [DataStax Astra DB](https://w
 
 ## Methods
 
-### createIndex()
+### `createIndex()`
 
 **indexName** (`string`): Name of the index to create
 
@@ -20,7 +20,7 @@ The AstraVector class provides vector search using [DataStax Astra DB](https://w
 
 **metric** (`'cosine' | 'euclidean' | 'dotproduct'`): Distance metric for similarity search (maps to dot\_product for dotproduct) (Default: `cosine`)
 
-### upsert()
+### `upsert()`
 
 **indexName** (`string`): Name of the index to upsert into
 
@@ -30,7 +30,7 @@ The AstraVector class provides vector search using [DataStax Astra DB](https://w
 
 **ids** (`string[]`): Optional vector IDs (auto-generated if not provided)
 
-### query()
+### `query()`
 
 **indexName** (`string`): Name of the index to query
 
@@ -42,11 +42,11 @@ The AstraVector class provides vector search using [DataStax Astra DB](https://w
 
 **includeVector** (`boolean`): Whether to include vectors in the results (Default: `false`)
 
-### listIndexes()
+### `listIndexes()`
 
 Returns an array of index names as strings.
 
-### describeIndex()
+### `describeIndex()`
 
 **indexName** (`string`): Name of the index to describe
 
@@ -60,11 +60,11 @@ interface IndexStats {
 }
 ```
 
-### deleteIndex()
+### `deleteIndex()`
 
 **indexName** (`string`): Name of the index to delete
 
-### updateVector()
+### `updateVector()`
 
 **indexName** (`string`): Name of the index containing the vector
 
@@ -72,13 +72,13 @@ interface IndexStats {
 
 **update** (`object`): Update object containing vector and/or metadata changes
 
-### deleteVector()
+### `deleteVector()`
 
 **indexName** (`string`): Name of the index containing the vector
 
 **id** (`string`): ID of the vector to delete
 
-## Response Types
+## Response types
 
 Query results are returned in this format:
 
@@ -91,7 +91,7 @@ interface QueryResult {
 }
 ```
 
-## Error Handling
+## Error handling
 
 The store throws typed errors that can be caught:
 
@@ -109,7 +109,7 @@ try {
 }
 ```
 
-## Environment Variables
+## Environment variables
 
 Required environment variables:
 

package/.docs/reference/vectors/chroma.md

@@ -1,4 +1,4 @@
-# Chroma Vector Store
+# Chroma vector store
 
 The ChromaVector class provides vector search using [Chroma](https://docs.trychroma.com/docs/overview/getting-started), an open-source embedding database. It offers efficient vector search with metadata filtering and hybrid search capabilities.
 
@@ -10,7 +10,7 @@ The ChromaVector class provides vector search using [Chroma](https://docs.trychr
 >
 > [Get started with Chroma Cloud](https://trychroma.com/signup)
 
-## Constructor Options
+## Constructor options
 
 **host** (`string`): The host address of the Chroma server. Defaults to 'localhost'
 
@@ -28,9 +28,9 @@ The ChromaVector class provides vector search using [Chroma](https://docs.trychr
 
 **fetchOptions** (`RequestInit`): Additional fetch options for HTTP requests
 
-## Running a Chroma Server
+## Running a Chroma server
 
-If you are a Chroma Cloud user, simply provide the `ChromaVector` constructor your API key, tenant, and database name.
+If you are a Chroma Cloud user, provide the `ChromaVector` constructor your API key, tenant, and database name.
 
 When you install the `@mastra/chroma` package, you get access to the [Chroma CLI](https://docs.trychroma.com/docs/cli/db), which can set these as environment variables for you: `chroma db connect [DB-NAME] --env-file`.
 
@@ -42,7 +42,7 @@ Otherwise, you have several options for setting up your single-node Chroma serve
 
 ## Methods
 
-### createIndex()
+### `createIndex()`
 
 **indexName** (`string`): Name of the index to create
 
@@ -50,17 +50,17 @@ Otherwise, you have several options for setting up your single-node Chroma serve
 
 **metric** (`'cosine' | 'euclidean' | 'dotproduct'`): Distance metric for similarity search (Default: `cosine`)
 
-### forkIndex()
+### `forkIndex()`
 
 Note: Forking is only supported on Chroma Cloud, or if you deploy your own OSS **distributed** Chroma.
 
-`forkIndex` lets you fork an existing Chroma index instantly. Operations on the forked index do not affect the original one. Learn more on the [Chroma docs](https://docs.trychroma.com/cloud/collection-forking).
+`forkIndex` lets you fork an existing Chroma index instantly. Operations on the forked index don't affect the original one. Learn more on the [Chroma docs](https://docs.trychroma.com/cloud/collection-forking).
 
 **indexName** (`string`): Name of the index to fork
 
 **newIndexName** (`string`): The name of the forked index
 
-### upsert()
+### `upsert()`
 
 **indexName** (`string`): Name of the index to upsert into
 
@@ -72,7 +72,7 @@ Note: Forking is only supported on Chroma Cloud, or if you deploy your own OSS *
 
 **documents** (`string[]`): Chroma-specific: Original text documents associated with the vectors
 
-### query()
+### `query()`
 
 Query an index using a `queryVector`. Returns an array of semantically similar records in order of distance from the `queryVector`. Each record has the shape:
 
@@ -100,7 +100,7 @@ You can also provide the shape of your metadata to a `query` call for type infer
 
 **documentFilter** (`Record<string, any>`): Chroma-specific: Filter to apply on the document content
 
-### get()
+### `get()`
 
 Get records from your Chroma index by IDs, metadata, and document filters. It returns an array of records of the shape:
 
@@ -129,11 +129,11 @@ You can also provide the shape of your metadata to a `get` call for type inferen
 
 **offset** (`number`): Offset for returning records. Use with \`limit\` to paginate results.
 
-### listIndexes()
+### `listIndexes()`
 
 Returns an array of index names as strings.
 
-### describeIndex()
+### `describeIndex()`
 
 **indexName** (`string`): Name of the index to describe
 
@@ -147,11 +147,11 @@ interface IndexStats {
 }
 ```
 
-### deleteIndex()
+### `deleteIndex()`
 
 **indexName** (`string`): Name of the index to delete
 
-### updateVector()
+### `updateVector()`
 
 Update a single vector by ID or by metadata filter. Either `id` or `filter` must be provided, but not both.
 
@@ -187,13 +187,13 @@ await vectorStore.updateVector({
 })
 ```
 
-### deleteVector()
+### `deleteVector()`
 
 **indexName** (`string`): Name of the index containing the vector to delete
 
 **id** (`string`): ID of the vector to delete
 
-### deleteVectors()
+### `deleteVectors()`
 
 Delete multiple vectors by IDs or by metadata filter. This method enables bulk deletion and source-based vector management. Either `ids` or `filter` must be provided, but not both.
 
@@ -227,7 +227,7 @@ await vectorStore.deleteVectors({
 })
 ```
 
-## Response Types
+## Response types
 
 Query results are returned in this format:
 
@@ -241,7 +241,7 @@ interface QueryResult {
 }
 ```
 
-## Error Handling
+## Error handling
 
 The store throws typed errors that can be caught: