Skip to main content
Glama

ner_extract

Extract medical named entities from clinical text, including ICD-10, CPT codes, medications, and dates with confidence scores.

Instructions

Extract medical named entities from clinical text. Identifies ICD-10 codes, CPT codes, dates, medications, and 12 entity types with confidence scores.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesClinical text to extract entities from
entityTypesNoFilter to specific entity types

Implementation Reference

  • Zod schema definition and tool metadata for ner_extract. Defines the tool name, description, price, endpoint '/agent/v1/ner/extract', and input schema (text: required string, entityTypes: optional array of strings).
    {
      name: 'ner_extract',
      description: 'Extract medical named entities from clinical text. Identifies ICD-10 codes, CPT codes, dates, medications, and 12 entity types with confidence scores.',
      price: '$0.02',
      endpoint: '/agent/v1/ner/extract',
      schema: {
        text: z.string().describe('Clinical text to extract entities from'),
        entityTypes: z.array(z.string()).optional().describe('Filter to specific entity types'),
      },
    },
  • src/index.js:19-61 (registration)
    Registration of the ner_extract tool as an MCP tool via server.tool(). The generic handler fetches the external REST API at the tool's endpoint. ner_extract is registered as part of the MCP_TOOLS loop at line 19.
    for (const tool of MCP_TOOLS) {
      s.tool(tool.name, tool.description, tool.schema, async (params) => {
        const toolDef = getToolByName(tool.name);
        if (!toolDef) {
          return { content: [{ type: 'text', text: `Unknown tool: ${tool.name}` }], isError: true };
        }
        try {
          const response = await fetch(`${API_BASE_URL}${toolDef.endpoint}`, {
            method: 'POST',
            headers: {
              'Content-Type': 'application/json',
              ...(API_KEY && { 'X-API-Key': API_KEY }),
              'X-Agent-ID': 'mcp-client',
              'User-Agent': '@mymedi-ai/mcp-server/1.2.1',
            },
            body: JSON.stringify(params),
          });
          if (response.status === 402) {
            const paymentInfo = await response.json();
            return {
              content: [{ type: 'text', text: JSON.stringify({
                error: 'payment_required',
                message: `This tool costs ${toolDef.price} per call. Register at ${API_BASE_URL}/bot-marketplace/register for an API key with 10 free starter credits, or pay per call with on-chain USDC (no signup) via the x402 protocol.`,
                price: toolDef.price, register: `${API_BASE_URL}/bot-marketplace/register`, ...paymentInfo,
              }, null, 2) }], isError: true,
            };
          }
          if (!response.ok) {
            const error = await response.json().catch(() => ({ message: response.statusText }));
            return { content: [{ type: 'text', text: JSON.stringify({ error: true, status: response.status, ...error }, null, 2) }], isError: true };
          }
          const data = await response.json();
          const creditsSpent = response.headers.get('X-Credits-Spent');
          const creditsRemaining = response.headers.get('X-Credits-Remaining');
          if (creditsSpent) {
            data._billing = { creditsSpent: parseInt(creditsSpent, 10), creditsRemaining: creditsRemaining ? parseInt(creditsRemaining, 10) : undefined, priceUSD: toolDef.price };
          }
          return { content: [{ type: 'text', text: JSON.stringify(data, null, 2) }] };
        } catch (err) {
          return { content: [{ type: 'text', text: JSON.stringify({ error: true, message: err.message, hint: 'Ensure MCP_API_BASE_URL and MCP_API_KEY environment variables are set.' }, null, 2) }], isError: true };
        }
      });
    }
  • src/index.js:66-73 (registration)
    Sandbox registration of ner_extract in createSandboxServer(), returning 'sandbox' placeholder responses.
    export function createSandboxServer() {
      const sandboxServer = new McpServer({ name: 'mymedi-ai', version: '1.2.1' });
      for (const tool of MCP_TOOLS) {
        sandboxServer.tool(tool.name, tool.description, tool.schema,
          async () => ({ content: [{ type: 'text', text: 'sandbox' }] }));
      }
      return sandboxServer;
    }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavior. It mentions output includes confidence scores, but omits crucial details: whether the tool is read-only, if it requires specific authentication, or any side effects. The agent cannot assess safety or side effects from this description alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no wasted words. The verb+resource pattern is front-loaded. Every sentence adds unique information: first sentence states action and domain, second sentence lists notable outputs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description partially compensates by mentioning confidence scores but does not detail the structure of extracted entities (e.g., format, nesting, or error scenarios). It is adequate for a simple extraction tool but leaves some gaps for an agent to infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds value by explaining what the extraction produces (specific entity types and confidence scores), which clarifies the purpose of the 'entityTypes' filter parameter. This goes beyond the schema's basic descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Extract' and the resource 'medical named entities from clinical text'. It lists specific entity types (ICD-10, CPT, dates, medications, and 12 entity types) with confidence scores, distinguishing it from sibling tools like code_lookup or drug_lookup which are lookups rather than extractions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. The description does not state when not to use it or provide references to sibling tools. The context is implied by the extraction focus, but no proactive help for agent selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MyMedi-AI/mymedi-ai-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server