Skip to main content
Glama
kesslerio

Attio MCP Server

by kesslerio

aaa-health-check

Read-onlyIdempotent

Check the operational status of the Attio MCP Server to verify system availability and connectivity without authentication requirements.

Instructions

Returns server status without requiring any credentials.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Core handler function implementing aaa-health-check tool logic. Detects runtime environment, echoes input, returns formatted JSON health status.
    export async function handleHealthCheck(params: {
      echo?: string;
    }): Promise<ToolResult> {
      const payload = {
        ok: true,
        name: 'attio-mcp-core',
        version: '0.1.0',
        echo: params.echo,
        timestamp: new Date().toISOString(),
        runtime:
          typeof (globalThis as Record<string, unknown>).Deno !== 'undefined'
            ? 'deno'
            : typeof (globalThis as Record<string, unknown>).Bun !== 'undefined'
              ? 'bun'
              : typeof (globalThis as Record<string, unknown>).caches !==
                  'undefined'
                ? 'cloudflare-workers'
                : 'node',
      };
    
      return successResult(JSON.stringify(payload, null, 2));
    }
  • Tool schema definition including name, description, input schema (optional echo string), and annotations for read-only/idempotent usage.
    export const healthCheckDefinition: ToolDefinition = {
      name: 'aaa-health-check',
      description: formatDescription({
        capability:
          'Run a lightweight health probe that echoes deployment metadata.',
        boundaries: 'query Attio APIs, mutate data, or require credentials.',
        constraints:
          'Accepts optional echo text; returns JSON payload as text for MCP clients.',
        recoveryHint:
          'If unavailable, review server logs or restart the server process.',
      }),
      inputSchema: {
        type: 'object',
        properties: {
          echo: {
            type: 'string',
            description: 'Optional text to echo back in the response',
          },
        },
        additionalProperties: true,
      },
      annotations: {
        readOnlyHint: true,
        idempotentHint: true,
      },
    };
  • Registration of aaa-health-check in the core tool handler dispatcher map, delegating to handleHealthCheck function.
    'aaa-health-check': async (_client, params) =>
      handleHealthCheck(params as { echo?: string }),
  • Inclusion of aaa-health-check in read-only tools set for search-only mode filtering.
    const READ_ONLY_TOOLS = new Set([
      'aaa-health-check',
  • Alternative/server-specific handler configuration for aaa-health-check with Node.js environment detection and MCP-compliant response formatting.
    export const healthCheckConfig = {
      name: 'aaa-health-check',
      handler: async (params: { [key: string]: unknown }) => {
        const payload = {
          ok: true,
          name: 'attio-mcp',
          echo:
            typeof params?.echo === 'string' ? (params.echo as string) : undefined,
          timestamp: new Date().toISOString(),
          environment: process.env.NODE_ENV || 'production',
          needs_api_key: true,
        } as const;
    
        // Return MCP-compliant text response (not JSON type)
        // MCP SDK expects content type to be 'text', not 'json'
        return {
          content: [
            {
              type: 'text',
              text: JSON.stringify(payload, null, 2),
            },
          ],
          isError: false,
        };
      },
      formatResult: (res: Record<string, unknown>): string => {
        const content = res?.content as Array<Record<string, unknown>> | undefined;
        const textContent = content?.[0]?.text as string | undefined;
    
        // Parse JSON from text content if available
        let data: Record<string, unknown>;
        if (textContent) {
          try {
            data = JSON.parse(textContent) as Record<string, unknown>;
          } catch {
            data = res;
          }
        } else {
          data = res;
        }
    
        const parts: string[] = ['✅ Server healthy'];
        if (data?.echo) parts.push(`echo: ${String(data.echo)}`);
        if (data?.environment) parts.push(`env: ${String(data.environment)}`);
        return parts.join(' | ');
      },
    };
Behavior4/5

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

The description adds valuable context beyond annotations: it specifies that no credentials are required, which isn't covered by readOnlyHint or idempotentHint. Annotations already indicate it's safe (read-only, idempotent), so the bar is lower, but the credential-free aspect is a useful behavioral trait that enhances transparency.

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?

The description is a single, efficient sentence that front-loads the key information: it states what the tool does and a critical constraint (no credentials needed). Every word earns its place, with no redundancy or unnecessary details.

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?

Given the tool's simplicity (0 parameters, no output schema) and rich annotations (readOnlyHint, idempotentHint), the description is nearly complete. It covers purpose, usage, and a key behavioral trait. A minor gap is the lack of detail on what 'server status' includes, but with annotations ensuring safety, this is acceptable.

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?

With 0 parameters and 100% schema description coverage, the baseline is 4. The description reinforces this by stating 'without requiring any credentials,' which aligns with the empty input schema, adding clarity that no inputs are needed for this operation.

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 explicitly states the verb ('Returns') and resource ('server status'), making the purpose clear. It also distinguishes itself from siblings by specifying it doesn't require credentials, which is unique among the listed tools that mostly involve data manipulation or retrieval requiring authentication.

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

Usage Guidelines5/5

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

The description provides explicit guidance on when to use this tool: for checking server status without credentials. It implies an alternative scenario where other tools might require credentials, helping differentiate it from siblings that likely need authentication for operations like create, delete, or search.

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/kesslerio/attio-mcp-server'

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