chore(mcp)!: remove deprecated tool schemes

This removes all tool schemes except for "code mode" tools. Specifically, this removes "all tools" and "dynamic tools" schemes. Additionally, this removes support for resource filtering, tags, jq filtering, and compatibility controls in MCP servers, as they are no longer necessary when using code mode.

# Migration

To migrate, simply modify the command used to invoke the MCP server. Currently, the only supported tool scheme is code mode. Now, starting the server with just `node /path/to/mcp/server` or `npx package-name` will invoke code tools: changing your command to one of these is likely all you will need to do.

Specifically, you must remove all flags including things like --resources, --tags, --client, --tools=dynamic, etc from your invocation command. The only supported flags are now `--port`, `--transport`, `--socket`, and `--tools=docs` (specifically for "docs"). These are also the only options available for http servers.

migration-effort: small

Author: stainless-app[bot]

packages/mcp-server/Dockerfile

@@ -39,9 +39,6 @@
 
     # Production stage
 
-            FROM denoland/deno:alpine
-            RUN apk add --no-cache npm
-
     # Add non-root user
     RUN addgroup -g 1001 -S nodejs && adduser -S nodejs -u 1001
 
@@ -66,10 +63,6 @@ COPY --from=builder /build/packages/mcp-server/node_modules ./node_modules
     # The MCP server uses stdio transport by default
     # No exposed ports needed for stdio communication
 
-    # This is needed for node to run on the deno:alpine image.
-    # See <https://github.com/denoland/deno_docker/issues/373>.
-    ENV LD_LIBRARY_PATH=/usr/lib:/usr/local/lib
-
     # Set the entrypoint to the MCP server
     ENTRYPOINT ["node", "index.js"]
 

packages/mcp-server/README.md

@@ -26,7 +26,7 @@ For clients with a configuration JSON, it might look something like this:
   "mcpServers": {
     "hyperspell_api": {
       "command": "npx",
-      "args": ["-y", "hyperspell-mcp", "--client=claude", "--tools=all"],
+      "args": ["-y", "hyperspell-mcp"],
       "env": {
         "HYPERSPELL_API_KEY": "My API Key",
         "HYPERSPELL_USER_ID": "My User ID"
@@ -59,110 +59,22 @@ environment variables in Claude Code's `.claude.json`, which can be found in you
 claude mcp add --transport stdio hyperspell_api --env HYPERSPELL_API_KEY="Your HYPERSPELL_API_KEY here." HYPERSPELL_USER_ID="Your HYPERSPELL_USER_ID here." -- npx -y hyperspell-mcp
 ```
 
-## Exposing endpoints to your MCP Client
+## Code Mode
 
-There are three ways to expose endpoints as tools in the MCP server:
+This MCP server is built on the "Code Mode" tool scheme. In this MCP Server,
+your agent will write code against the TypeScript SDK, which will then be executed in an
+isolated sandbox. To accomplish this, the server will expose two tools to your agent:
 
-1. Exposing one tool per endpoint, and filtering as necessary
-2. Exposing a set of tools to dynamically discover and invoke endpoints from the API
-3. Exposing a docs search tool and a code execution tool, allowing the client to write code to be executed against the TypeScript client
+- The first tool is a docs search tool, which can be used to generically query for
+  documentation about your API/SDK.
 
-### Filtering endpoints and tools
+- The second tool is a code tool, where the agent can write code against the TypeScript SDK.
+  The code will be executed in a sandbox environment without web or filesystem access. Then,
+  anything the code returns or prints will be returned to the agent as the result of the
+  tool call.
 
-You can run the package on the command line to discover and filter the set of tools that are exposed by the
-MCP Server. This can be helpful for large APIs where including all endpoints at once is too much for your AI's
-context window.
-
-You can filter by multiple aspects:
-
-- `--tool` includes a specific tool by name
-- `--resource` includes all tools under a specific resource, and can have wildcards, e.g. `my.resource*`
-- `--operation` includes just read (get/list) or just write operations
-
-### Dynamic tools
-
-If you specify `--tools=dynamic` to the MCP server, instead of exposing one tool per endpoint in the API, it will
-expose the following tools:
-
-1. `list_api_endpoints` - Discovers available endpoints, with optional filtering by search query
-2. `get_api_endpoint_schema` - Gets detailed schema information for a specific endpoint
-3. `invoke_api_endpoint` - Executes any endpoint with the appropriate parameters
-
-This allows you to have the full set of API endpoints available to your MCP Client, while not requiring that all
-of their schemas be loaded into context at once. Instead, the LLM will automatically use these tools together to
-search for, look up, and invoke endpoints dynamically. However, due to the indirect nature of the schemas, it
-can struggle to provide the correct properties a bit more than when tools are imported explicitly. Therefore,
-you can opt-in to explicit tools, the dynamic tools, or both.
-
-See more information with `--help`.
-
-All of these command-line options can be repeated, combined together, and have corresponding exclusion versions (e.g. `--no-tool`).
-
-Use `--list` to see the list of available tools, or see below.
-
-### Code execution
-
-If you specify `--tools=code` to the MCP server, it will expose just two tools:
-
-- `search_docs` - Searches the API documentation and returns a list of markdown results
-- `execute` - Runs code against the TypeScript client
-
-This allows the LLM to implement more complex logic by chaining together many API calls without loading
-intermediary results into its context window.
-
-The code execution itself happens in a Deno sandbox that has network access only to the base URL for the API.
-
-### Specifying the MCP Client
-
-Different clients have varying abilities to handle arbitrary tools and schemas.
-
-You can specify the client you are using with the `--client` argument, and the MCP server will automatically
-serve tools and schemas that are more compatible with that client.
-
-- `--client=<type>`: Set all capabilities based on a known MCP client
-
-  - Valid values: `openai-agents`, `claude`, `claude-code`, `cursor`
-  - Example: `--client=cursor`
-
-Additionally, if you have a client not on the above list, or the client has gotten better
-over time, you can manually enable or disable certain capabilities:
-
-- `--capability=<name>`: Specify individual client capabilities
-  - Available capabilities:
-    - `top-level-unions`: Enable support for top-level unions in tool schemas
-    - `valid-json`: Enable JSON string parsing for arguments
-    - `refs`: Enable support for $ref pointers in schemas
-    - `unions`: Enable support for union types (anyOf) in schemas
-    - `formats`: Enable support for format validations in schemas (e.g. date-time, email)
-    - `tool-name-length=N`: Set maximum tool name length to N characters
-  - Example: `--capability=top-level-unions --capability=tool-name-length=40`
-  - Example: `--capability=top-level-unions,tool-name-length=40`
-
-### Examples
-
-1. Filter for read operations on cards:
-
-```bash
---resource=cards --operation=read
-```
-
-2. Exclude specific tools while including others:
-
-```bash
---resource=cards --no-tool=create_cards
-```
-
-3. Configure for Cursor client with custom max tool name length:
-
-```bash
---client=cursor --capability=tool-name-length=40
-```
-
-4. Complex filtering with multiple criteria:
-
-```bash
---resource=cards,accounts --operation=read --tag=kyc --no-tool=create_cards
-```
+Using this scheme, agents are capable of performing very complex tasks deterministically
+and repeatably.
 
 ## Running remotely
 
@@ -190,76 +102,3 @@ A configuration JSON for this server might look like this, assuming the server i
   }
 }
 ```
-
-The command-line arguments for filtering tools and specifying clients can also be used as query parameters in the URL.
-For example, to exclude specific tools while including others, use the URL:
-
-```
-http://localhost:3000?resource=cards&resource=accounts&no_tool=create_cards
-```
-
-Or, to configure for the Cursor client, with a custom max tool name length, use the URL:
-
-```
-http://localhost:3000?client=cursor&capability=tool-name-length%3D40
-```
-
-## Importing the tools and server individually
-
-```js
-// Import the server, generated endpoints, or the init function
-import { server, endpoints, init } from "hyperspell-mcp/server";
-
-// import a specific tool
-import listConnections from "hyperspell-mcp/tools/connections/list-connections";
-
-// initialize the server and all endpoints
-init({ server, endpoints });
-
-// manually start server
-const transport = new StdioServerTransport();
-await server.connect(transport);
-
-// or initialize your own server with specific tools
-const myServer = new McpServer(...);
-
-// define your own endpoint
-const myCustomEndpoint = {
-  tool: {
-    name: 'my_custom_tool',
-    description: 'My custom tool',
-    inputSchema: zodToJsonSchema(z.object({ a_property: z.string() })),
-  },
-  handler: async (client: client, args: any) => {
-    return { myResponse: 'Hello world!' };
-  })
-};
-
-// initialize the server with your custom endpoints
-init({ server: myServer, endpoints: [listConnections, myCustomEndpoint] });
-```
-
-## Available Tools
-
-The following tools are available in this MCP server.
-
-### Resource `connections`:
-
-- `list_connections` (`read`): Get accounts the user has connected
-
-### Resource `integrations`:
-
-- `list_integrations` (`read`): List all available integrations
-- `connect_integration` (`read`): Get a signed url to connect to a given integration. Use the `list_integrations` tool to find the correct `integration_id` for the required provider.
-
-### Resource `memories`:
-
-- `update_memory` (`write`): This tool lets you update memory in Hyperspell.
-- `add_memory` (`write`): This tool lets you add text, markdown, or JSON to the Hyperspell index so it can be searched later. It will return the `source` and `resource_id` that can be used to later retrieve the processed memory.
-- `get_memory` (`read`): This tool lets you retrieve a memory that has been previously indexed.
-- `search` (`write`): Search all memories indexed by Hyperspell. Set 'answer' to true to directly answer the query, or to 'false' to simply get all memories related to the query.
-- `upload_file` (`write`): This tool lets you upload a file to the Hyperspell index. It will return the `source` and `resource_id` that can be used to later retrieve the processed memory.
-
-### Resource `auth`:
-
-- `user_info` (`read`): Get basic info about the current user, including which integrations are currently enabled and which ones are available.

packages/mcp-server/src/code-tool.ts

@@ -1,6 +1,6 @@
 // File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
-import { Metadata, ToolCallResult, asTextContentResult } from './tools/types';
+import { McpTool, Metadata, ToolCallResult, asTextContentResult } from './types';
 import { Tool } from '@modelcontextprotocol/sdk/types.js';
 import { readEnv } from './server';
 import { WorkerSuccess } from './code-tool-types';
@@ -13,7 +13,7 @@ import { WorkerSuccess } from './code-tool-types';
  *
  * @param endpoints - The endpoints to include in the list.
  */
-export async function codeTool() {
+export function codeTool(): McpTool {
   const metadata: Metadata = { resource: 'all', operation: 'write', tags: [] };
   const tool: Tool = {
     name: 'execute',