Skip to main content
Glama

pa_predict

Predict prior authorization approval probability for a procedure. Returns approval likelihood, confidence level, estimated processing days, and contributing factors.

Instructions

Predict prior authorization approval probability for a procedure. Returns approval likelihood (0-1), confidence level, estimated processing days, and contributing factors.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
procedureCodeYesCPT/HCPCS procedure code
diagnosisCodesNoSupporting ICD-10 diagnosis codes
payerIdNoInsurance payer ID
patientAgeNoPatient age in years
patientGenderNo

Implementation Reference

  • Tool definition and Zod schema for 'pa_predict'. Defines inputs: procedureCode (required string), diagnosisCodes (optional array of strings), payerId (optional string), patientAge (optional number), patientGender (optional enum M/F/O). Maps to endpoint '/agent/v1/pa/predict'.
    {
      name: 'pa_predict',
      description: 'Predict prior authorization approval probability for a procedure. Returns approval likelihood (0-1), confidence level, estimated processing days, and contributing factors.',
      price: '$0.05',
      endpoint: '/agent/v1/pa/predict',
      schema: {
        procedureCode: z.string().describe('CPT/HCPCS procedure code'),
        diagnosisCodes: z.array(z.string()).optional().describe('Supporting ICD-10 diagnosis codes'),
        payerId: z.string().optional().describe('Insurance payer ID'),
        patientAge: z.number().optional().describe('Patient age in years'),
        patientGender: z.enum(['M', 'F', 'O']).optional(),
      },
  • src/index.js:19-61 (registration)
    Registration of all MCP tools (including pa_predict) via s.tool() call. The handler function is a generic proxy that calls the REST API endpoint (POST /agent/v1/pa/predict) with the user's params, passes the API key, and returns the JSON response as text.
    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 };
        }
      });
    }
  • The actual handler logic for pa_predict. It's a generic async handler registered for all tools: it takes params, fetches the tool's REST endpoint (for pa_predict: POST /agent/v1/pa/predict), handles 402 payment_required errors, handles non-ok responses, extracts billing headers, and returns the JSON response.
      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 };
        }
      });
    }
Behavior3/5

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

No annotations provided; description covers return values (likelihood, confidence, days, factors) but does not mention side effects, auth needs, or rate limits. Adequate for a read-like prediction tool.

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 efficiently deliver purpose and returns with no redundancy. Front-loaded with action verb and resource.

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

Completeness4/5

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

Covers key return elements but lacks caveats (e.g., model limitations, data recency). Adequate for a straightforward prediction tool given schema richness.

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

Parameters3/5

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

Schema description coverage is 80% (4 of 5 parameters described). The description adds no parameter-level details beyond schema, so meets baseline without improvement.

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 uses a specific verb 'Predict' and identifies the resource 'prior authorization approval probability', clearly distinguishing from sibling tools like pa_status (status check) or claims_validate.

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

Usage Guidelines3/5

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

Implied usage for predicting approval probability, but no explicit guidance on when to use vs alternatives (e.g., pa_status) or prerequisites like procedure code presence.

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