{
  "id": "testing-mcp-servers",
  "type": "entity",
  "name": "Testing MCP servers and integrations",
  "summary": "What reliability testing means for Model Context Protocol integrations: conformance to the JSON-RPC contract, capability-negotiation edge cases, and — because the spec itself declares tool descriptions untrusted — injection probes through every server-supplied string. An MCP interface is an API whose consumer is a model, so its test suite gates on success rate like any other API, plus adversarial content like no other API.",
  "locale": "en",
  "tags": [
    "mcp",
    "testing",
    "integrations",
    "protocols",
    "security"
  ],
  "relations": [
    {
      "rel": "related",
      "target": "prompt-injection-testing"
    },
    {
      "rel": "related",
      "target": "agent-observability-standards"
    },
    {
      "rel": "related",
      "target": "red-teaming-your-agent"
    }
  ],
  "questions": [
    "How do I test an MCP server?",
    "Are MCP tool descriptions trustworthy?",
    "What should an MCP integration's release gate measure?"
  ],
  "claims": [
    {
      "id": "c1",
      "text": "MCP standardizes stateful JSON-RPC 2.0 connections between hosts, clients and servers with capability negotiation; servers expose tools, resources and prompts, and clients may offer sampling, roots and elicitation — each a distinct surface a conformance suite must cover.",
      "sources": [
        "mcp-spec"
      ],
      "confidence": 0.95
    },
    {
      "id": "c2",
      "text": "The specification itself instructs implementors to treat tool behavior descriptions and annotations as untrusted unless they come from a trusted server, to treat tools as arbitrary code execution, and to require explicit user consent before any tool invocation — making description-borne injection a spec-named test case, not a hypothetical.",
      "sources": [
        "mcp-spec"
      ],
      "confidence": 0.95
    },
    {
      "id": "c3",
      "text": "MCP telemetry is standardizable today: OpenTelemetry's GenAI semantic conventions include MCP alongside model and agent spans, so integration health can be measured with shared vocabulary.",
      "sources": [
        "otel-genai-semconv"
      ],
      "confidence": 0.85
    },
    {
      "id": "c4",
      "text": "A production example of gating on it: this instance's blueprint ships an MCP interface and declares a minimum MCP success rate of 0.99 among its release thresholds.",
      "sources": [
        "citarium-methodology-brief"
      ],
      "confidence": 0.9
    }
  ],
  "takeaways": [],
  "faqs": [],
  "evidence_tier": "primary",
  "evidence": {
    "level": "production",
    "source_types": [
      "production_system",
      "personal_experience",
      "industry_observation"
    ]
  },
  "moat_flag": true,
  "winning_edge": "Derives the test plan from the spec's own security text (untrusted descriptions, consent boundaries) instead of generic API-testing advice, and shows a real release gate with an MCP success threshold — a topic with plenty of tutorials and almost no testing literature.",
  "confidence": 0.85,
  "last_verified": "2026-08-08",
  "canonical_url": "https://agentreliability.dev/k/testing-mcp-servers",
  "api_url": "https://agentreliability.dev/api/k/testing-mcp-servers.json",
  "jsonld": {
    "@context": "https://schema.org",
    "name": "Testing MCP servers and integrations",
    "description": "What reliability testing means for Model Context Protocol integrations: conformance to the JSON-RPC contract, capability-negotiation edge cases, and — because the spec itself declares tool descriptions untrusted — injection probes through every server-supplied string. An MCP interface is an API whose consumer is a model, so its test suite gates on success rate like any other API, plus adversarial content like no other API.",
    "url": "https://agentreliability.dev/k/testing-mcp-servers",
    "license": "https://spdx.org/licenses/CC-BY-4.0.html",
    "dateModified": "2026-08-08",
    "citation": [
      {
        "@type": "CreativeWork",
        "name": "agent-reliability editorial brief and blueprint (Gate 1 approved, 2026-08-08)"
      },
      {
        "@type": "CreativeWork",
        "name": "OpenTelemetry semantic conventions for generative AI",
        "url": "https://github.com/open-telemetry/semantic-conventions-genai"
      },
      {
        "@type": "CreativeWork",
        "name": "Model Context Protocol specification (2025-06-18)",
        "url": "https://modelcontextprotocol.io/specification/2025-06-18"
      }
    ],
    "author": {
      "@type": "Person",
      "name": "Santiago Santa María Morales",
      "jobTitle": "practitioner — harness engineering and agent evaluation in production"
    },
    "@type": "Article",
    "headline": "Testing MCP servers and integrations"
  }
}