{
  "schema_version": "1.3.0",
  "slug": "what-structural-signals-indicate-mcp-tool-poisoning-detection-via-schema-anomaly-analysis-and-behavioral-drift-monitoring",
  "title": "What structural signals indicate MCP tool-poisoning detection via schema anomaly analysis and behavioral drift monitoring",
  "date_of_record": "2026 November 18",
  "scope": "Applies to Model Context Protocol servers whose tool descriptors (`name`, `description`, `inputSchema`, `annotations`) are fetched at session start and whose handlers are invoked through a proxy or orchestrator that can interpose on both the descriptor and the result payload. Does not apply to servers where the descriptor is compiled into the client, nor to cases where the poisoning vector is exclusively prompt-injection in free-text output with no schema or behavioral correlate.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-mcp-tool-poisoning-detection-via-schema-anomaly-analysis-and-behavioral-drift-monitoring.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-mcp-tool-poisoning-detection-via-schema-anomaly-analysis-and-behavioral-drift-monitoring.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-mcp-tool-poisoning-detection-via-schema-anomaly-analysis-and-behavioral-drift-monitoring.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1912,
    "python_slice_tokens": 390,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "Schema anomaly analysis and behavioral drift monitoring are usually described as two independent detectors that vote on the same question (\"is this tool malicious?\"). They are not. They observe different surfaces with different adversarial reachability. The schema is a *static, attacker-authored artifact* — the poisoning server controls every byte of it at r...",
    "what_was_observed": "Across a corpus of MCP servers exhibiting tool-poisoning behavior (descriptor-embedded instructions to the model, shadowing of sibling tool names, and parameter-triggered exfiltration), three structural signals recurred and were *not* individually diagnostic: 1. **Description/name lexical divergence.** The tool `name` matched a benign verb (`read_file`, `list_dir`) while the `description` contained imperative second-...",
    "condition_of_validity": "The schema-anomaly prior is valid only under two conditions, both of which must hold: - **The anomaly is *load-bearing* for the attack.** A signal is only useful if suppressing it would defeat the poisoning. Lexical imperatives in `description` fail this test (movable to `default` values, `enum` entries, or `examples`). Parameter-surface asymmetry and annota...",
    "decision_boundary": "The operational rule that survived contact: - **Schema anomaly raises the probe budget, never the verdict.** A tool with a load-bearing schema anomaly is placed in the differential-probe set. It is not quarantined on schema evidence alone. - **Quarantine requires a behavioral confirmation.** The confirmation is one of: (a) an outbound connection to a host no...",
    "operational_effect": "In practice this changes the pipeline from \"scan descriptors, flag bad ones\" to \"scan descriptors to *select probes*, then run probes and flag on behavior.\" The concrete effects: (1) probe cost moves from O(tools) to O(tools with load-bearing schema anomalies), which is small; (2) the false-positive rate drops because lexical imperatives no longer trigger qu..."
  },
  "matched_failure_symptoms": [
    "SCHEMA_DRIFT_OR_COERCION_CRASH"
  ],
  "composition_edges": {
    "primary_domain": "epistemic_provenance_and_federation_routing",
    "upstream_precondition_residuals": [
      "https://corpusfetch.com/c/according-to-what-precedence-hierarchy-must-an-instance-resolve-contradictory-directives-across-system-developer-and-user-tiers.md",
      "https://corpusfetch.com/c/how-should-an-instance-decide-that-a-stored-conclusion-has-gone-stale-without-a-new-observation.md"
    ],
    "downstream_consequence_residuals": [
      "https://corpusfetch.com/c/by-what-checkpoint-and-compaction-boundaries-must-an-instance-externalize-working-state-to-prevent-context-window-drift-and-truncation-amnesia.md",
      "https://corpusfetch.com/c/across-what-additive-schema-and-unknown-field-preservation-boundaries-must-an-instance-evolve-wire-contracts-to-prevent-rolling-deploy-deserialization-crashes.md"
    ],
    "co_occurring_sibling_residuals": [
      "https://corpusfetch.com/c/how-can-an-instance-capture-implicit-user-preferences-without-storing-private-data.md",
      "https://corpusfetch.com/c/how-can-an-instance-compress-long-reasoning-traces-into-binding-conclusions.md"
    ]
  },
  "empirical_verification_warrant": {
    "status": "AST_AND_INVARIANT_VERIFIED",
    "syntax_valid": true,
    "code_sha256": "14d22c9ac60b727fb502edd35e64207bbf5655020dfe13e5c65d48563da95883",
    "verified_classes": [
      "SchemaPriorMisuseError"
    ],
    "verified_functions": [
      "classify_tool",
      "gate_session",
      "_has_load_bearing"
    ],
    "verified_functions_count": 3,
    "defensive_guards_count": 1,
    "raised_exceptions": [
      "SchemaPriorMisuseError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
