mcpprobe-scanner 0.3.2__py3-none-any.whl → 0.3.3__py3-none-any.whl

mcpprobe/__init__.py

@@ -13,7 +13,7 @@ The package is organised as follows:
 
 from __future__ import annotations
 
-__version__ = "0.3.2"
+__version__ = "0.3.3"
 
 POLICY_URL = "https://mcpprobe.tech/scanning-policy"
 USER_AGENT = f"mcpprobe/{__version__} (+{POLICY_URL})"

mcpprobe/checks/auth.py

@@ -401,7 +401,7 @@ class Auth03AuthorizationServerMetadata(Check):
                 "metadata is missing (AUTH-02).",
                 related_to="AUTH-02",
             )
-        servers = [s for s in prm.get("authorization_servers") or [] if isinstance(s, str)]
+        servers = list(dict.fromkeys(s for s in prm.get("authorization_servers") or [] if isinstance(s, str)))
         if not servers:
             raise NotApplicable(
                 "The protected resource metadata lists no authorization server (AUTH-02).",
@@ -501,6 +501,7 @@ class Auth03AuthorizationServerMetadata(Check):
                         confidence=Confidence.HIGH,
                         evidence=evidence_of(*responses),
                         location=issuer,
+                        variant="plain-http-endpoints",
                         details={"insecure_endpoints": insecure},
                         affected=insecure,
                         proof=doc_proof,
@@ -511,6 +512,7 @@ class Auth03AuthorizationServerMetadata(Check):
                 findings.append(
                     self.finding(
                         title="Authorization server issuer mismatch",
+                        variant="issuer-mismatch",
                         description=f"Metadata issuer {doc['issuer']!r} differs from advertised {issuer!r}.",
                         severity=Severity.LOW,
                         confidence=Confidence.MEDIUM,
@@ -625,6 +627,8 @@ class Auth04TokenAudienceAndPassthrough(Check):
                         else "The response was 2xx but carried no JSON-RPC result, so acceptance is inferred from the status only.",
                         evidence=evidence_of(resp),
                         location=ctx.target,
+                        # Both self-minted tokens can be accepted; the second needs its own uid.
+                        variant=None if label == "HS256/random-key" else "alg-none",
                         details={"probe": label, "claims": now_claims},
                         affected=[label],
                         proof=proof.exchange(

mcpprobe/checks/base.py

@@ -186,6 +186,7 @@ class Check(abc.ABC):
         confidence: Confidence = Confidence.HIGH,
         evidence: list[EvidenceRecord] | None = None,
         location: str | None = None,
+        variant: str | None = None,
         fix: str | None = None,
         details: dict[str, Any] | None = None,
         title: str | None = None,
@@ -198,7 +199,9 @@ class Check(abc.ABC):
         """Build a :class:`Finding` pre-filled from the check's metadata.
 
         ``excerpt`` overrides the evidence excerpt that is otherwise derived from
-        the first evidence record. A finding whose confidence is not high must
+        the first evidence record. ``variant`` must be set on every finding after
+        the first that the check can report at the same ``location`` in one scan,
+        so each finding keeps a distinct, stable ``uid``. A finding whose confidence is not high must
         say why (``confidence_reason``); this is enforced so no label goes unexplained.
         """
         records = [e for e in (evidence or []) if e is not None]
@@ -215,6 +218,7 @@ class Check(abc.ABC):
             evidence=records,
             evidence_excerpt=excerpt if excerpt is not None else evidence_excerpt(records),
             location=location,
+            variant=variant,
             details=details or {},
             false_positive_notes=self.false_positive_notes or None,
             confidence_reason=confidence_reason,

mcpprobe/checks/baseline.py

@@ -204,6 +204,7 @@ class Meta02RugPullBaseline(Check):
             out.append(
                 self.finding(
                     title="Tools removed since baseline",
+                    variant="removed",
                     description="Removed tools: " + ", ".join(tools["removed"]) + ".",
                     severity=Severity.INFO,
                     confidence=Confidence.HIGH,

mcpprobe/checks/metadata.py

@@ -206,6 +206,7 @@ class Meta03DangerousCapabilitySurface(Check):
             findings.append(
                 self.finding(
                     title="High-impact tool capabilities exposed",
+                    variant="high-impact",
                     description="Tools classified as high-impact: "
                     + summary
                     + ". Review that each is necessary, scoped and gated by user approval.",
@@ -354,6 +355,7 @@ class Meta04SchemaHygiene(Check):
             findings.append(
                 self.finding(
                     title="Duplicate tool names",
+                    variant="duplicate-names",
                     description="Tool names listed more than once: " + ", ".join(dupes) + ".",
                     severity=Severity.MEDIUM,
                     confidence=Confidence.HIGH,

mcpprobe/checks/robustness.py

@@ -165,6 +165,7 @@ class Err01VerboseErrors(Check):
             findings.append(
                 self.finding(
                     title="Server header discloses software version",
+                    variant="server-header",
                     description=f"Server: {server_header}",
                     severity=Severity.INFO,
                     confidence=Confidence.HIGH,
@@ -281,6 +282,7 @@ class Dos01UnboundedConsumption(Check):
                 findings.append(
                     self.finding(
                         title=f"Server struggled with {label} request",
+                        variant=f"{label}-probe",
                         description=f"The {label} probe produced: {problem}. Input limits may be missing.",
                         severity=Severity.LOW if "slow" in problem else Severity.MEDIUM,
                         confidence=Confidence.MEDIUM,

mcpprobe/checks/transport_conformance.py

@@ -360,6 +360,7 @@ class Trans03SessionIdQuality(Check):
             findings.append(
                 self.finding(
                     title="Forged session ID accepted",
+                    variant="forged-session-id",
                     description=(
                         "tools/list with a random, never-issued Mcp-Session-Id was answered with a "
                         "result. The server does not validate session IDs (spec: 404 for unknown sessions)."
@@ -461,6 +462,7 @@ class Trans04DeprecatedTransport(Check):
             findings.append(
                 self.finding(
                     title="Pre-2025-06-18 protocol revision negotiated",
+                    variant="old-revision",
                     description=f"The server negotiated protocol revision {fp.protocol_version}, "
                     "which predates the current authorization and transport requirements.",
                     severity=Severity.INFO,
@@ -521,6 +523,7 @@ class Trans05TlsAndHeaders(Check):
             findings.append(
                 self.finding(
                     title="MCP endpoint served over plain HTTP",
+                    variant="plain-http",
                     description=(
                         "The endpoint is reachable over unencrypted HTTP; bearer tokens, session IDs "
                         "and tool data travel in the clear."
@@ -546,6 +549,7 @@ class Trans05TlsAndHeaders(Check):
             findings.append(
                 self.finding(
                     title="Weak TLS version negotiated",
+                    variant="weak-tls",
                     description=f"The connection negotiated {http.tls_version}.",
                     severity=Severity.MEDIUM,
                     confidence=Confidence.HIGH,

mcpprobe/models.py

@@ -7,10 +7,12 @@ report is a faithful, schema-stable serialisation of what the scanner saw.
 from __future__ import annotations
 
 import datetime as dt
+import hashlib
+import json
 from enum import Enum
 from typing import Any
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, computed_field
 
 #: Maximum number of body bytes retained per request/response in evidence.
 #: Proof excerpts are always built from parsed data, never from this copy.
@@ -145,6 +147,13 @@ class Finding(BaseModel):
         default=None,
         description="Where in the target the issue lives (tool name, header, URL path...)",
     )
+    variant: str | None = Field(
+        default=None,
+        description=(
+            "Distinguishes separate findings of one check at the same location "
+            "(e.g. 'forged-session-id'); None for the check's main finding"
+        ),
+    )
     details: dict[str, Any] = Field(default_factory=dict)
     false_positive_notes: str | None = None
     confidence_reason: str | None = Field(
@@ -162,10 +171,82 @@ class Finding(BaseModel):
         default_factory=list, description="IDs of the supporting evidence records"
     )
 
+    @computed_field  # type: ignore[prop-decorator]
+    @property
+    def uid(self) -> str:
+        """Identity of this finding, unique within a report and stable across scans.
+
+        ``<check id>:<location or ->``, plus ``:<variant>`` when the check reports more
+        than one thing at the same location. ``id`` stays the check ID (several findings
+        can share it); ``uid`` is what tells them apart.
+        """
+        base = f"{self.id}:{self.location or '-'}"
+        return f"{base}:{self.variant}" if self.variant else base
+
     @property
     def fingerprint(self) -> str:
-        """Stable identity for de-duplication across scans (used in SARIF)."""
-        return f"{self.id}:{self.location or '-'}"
+        """Stable identity for de-duplication across scans (SARIF ``partialFingerprints``)."""
+        return self.uid
+
+    def content_digest(self) -> str:
+        """Hash of what the finding says (not of its evidence), used to spot genuine duplicates."""
+        payload = json.dumps(
+            [
+                self.id,
+                self.location,
+                self.variant,
+                self.title,
+                self.severity.value,
+                self.description,
+                sorted(self.affected),
+                self.details,
+            ],
+            sort_keys=True,
+            default=str,
+            ensure_ascii=False,
+        )
+        return hashlib.sha256(payload.encode("utf-8")).hexdigest()
+
+
+def dedupe_findings(findings: list[Finding]) -> list[Finding]:
+    """Return ``findings`` with genuine duplicates merged and every ``uid`` unique.
+
+    Two findings with the same ``uid`` that say the same thing (same title, severity,
+    description, affected items and details) are one finding reported twice, for
+    example because the server listed the same tool twice; they are merged into the
+    first, keeping the union of their evidence. Findings that share a ``uid`` but say
+    different things are kept, and each gets a variant derived from its content (not
+    from its position), so the ``uid`` stays the same from one scan to the next.
+    Order is preserved.
+    """
+    by_uid: dict[str, list[Finding]] = {}
+    for f in findings:
+        by_uid.setdefault(f.uid, []).append(f)
+    if all(len(group) == 1 for group in by_uid.values()):
+        return list(findings)
+    keep: dict[int, Finding] = {}
+    for group in by_uid.values():
+        merged: dict[str, Finding] = {}
+        for f in group:
+            digest = f.content_digest()
+            first = merged.get(digest)
+            if first is None:
+                merged[digest] = f
+                keep[id(f)] = f
+            else:
+                _merge_into(first, f)
+        if len(merged) > 1:
+            for digest, f in merged.items():
+                f.variant = f"{f.variant}-{digest[:8]}" if f.variant else digest[:8]
+    return [f for f in findings if id(f) in keep]
+
+
+def _merge_into(target: Finding, dup: Finding) -> None:
+    seen = {e.id for e in target.evidence}
+    target.evidence.extend(e for e in dup.evidence if e.id not in seen)
+    for eid in dup.evidence_ids:
+        if eid not in target.evidence_ids:
+            target.evidence_ids.append(eid)
 
 
 class CheckStatus(str, Enum):

mcpprobe/scanner.py

@@ -22,6 +22,7 @@ from mcpprobe.models import (
     Fingerprint,
     Inventory,
     ScanReport,
+    dedupe_findings,
     utcnow,
 )
 from mcpprobe.policy import DEFAULT_RATE, check_opt_out, clamp_rate
@@ -247,7 +248,7 @@ async def run_check(check: Check, ctx: ScanContext) -> CheckResult:
     started = time.monotonic()
     throttled_before = ctx.transport.throttle_exhausted
     try:
-        result.findings = await check.run(ctx)
+        result.findings = dedupe_findings(await check.run(ctx))
     except NotApplicable as exc:
         result.status = CheckStatus.NOT_APPLICABLE
         result.reason = exc.reason
@@ -372,9 +373,12 @@ async def run_scan(config: ScanConfig) -> tuple[ScanReport, EvidenceLog]:
             report.checks.append(result)
             report.findings.extend(result.findings)
         report.notes.extend(ctx.notes)
+        # Each check's findings are already de-duplicated; this keeps the report-wide
+        # list (and so counts, max severity, chains and SARIF results) to one entry per uid.
+        report.findings = dedupe_findings(report.findings)
         report.chains = build_chains(report, ctx)
         report.readiness = build_readiness(report)
     report.finished_at = utcnow()
     report.evidence_count = len(evidence)
-    report.findings.sort(key=lambda f: (-f.severity.rank, f.id, f.location or ""))
+    report.findings.sort(key=lambda f: (-f.severity.rank, f.id, f.location or "", f.variant or ""))
     return report, evidence

{mcpprobe_scanner-0.3.2.dist-info → mcpprobe_scanner-0.3.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: mcpprobe-scanner
-Version: 0.3.2
+Version: 0.3.3
 Summary: Security scanner for Model Context Protocol (MCP) servers: auth, transport, tool-metadata and poisoning checks with JSON and SARIF output.
 Project-URL: Homepage, https://mcpprobe.tech
 Project-URL: Scanning policy, https://mcpprobe.tech/scanning-policy
@@ -202,7 +202,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: mcpprobe-dev/mcpprobe@v0.3.2
+      - uses: mcpprobe-dev/mcpprobe@v0.3.3
         id: scan
         with:
           target: https://staging.your-server.example/mcp

{mcpprobe_scanner-0.3.2.dist-info → mcpprobe_scanner-0.3.3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-mcpprobe/__init__.py,sha256=N9vKxA9eF1aDIFk3RgpPITsZNsvLMkF9HxNVYUGWd94,821
+mcpprobe/__init__.py,sha256=PNej_6ygJx84uJpIgm_HjldTy3UMcNcwp32ImaxuOmE,821
 mcpprobe/action.py,sha256=oHsoM82lKf9eBNjKvP9YM-ec0H_floAUxS5JKk8S1sQ,8760
 mcpprobe/authz.py,sha256=PCql53OFLQsN7oZxm2UtoAqTmT7LWRRw5nmx_50ePik,10595
 mcpprobe/catalogue.py,sha256=j0h-O-2FQq158P97bXf3akD0S3gzxt7P4AUJYMHbYss,4729
@@ -7,26 +7,26 @@ mcpprobe/cli.py,sha256=tC6nFYHrjxljqvv5BOc6vJfKDgdca8r7OwoQiEeAl1I,12871
 mcpprobe/dnsutil.py,sha256=d9AWtU96SHE7QzphZk76L9r61LpI0MuxPYLHEijHK4Y,1958
 mcpprobe/environment.py,sha256=9wbVmoJFXwGnqL4LHvt0D6dZupX650MjAgjq675xsyk,1937
 mcpprobe/governance.py,sha256=khs0t3jjSbwYzFYAjywnOzy_9m_qXy4ctuaFJy8UkdI,3391
-mcpprobe/models.py,sha256=ANK4SZdm0miYH0tg04QhWffrsa2v-5wjfdLqNSXDW28,14352
+mcpprobe/models.py,sha256=ALrCGIVYoMuvI373M86-McojPu4ZcXVAIGOew8pk_4I,17540
 mcpprobe/policy.py,sha256=VWb6R3Udetp3AFk-BJqulRJREquyvtvP1VS8QhUOMdo,4865
 mcpprobe/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mcpprobe/readiness.py,sha256=DzI09yU0PmcGmn8jZhfvVPgRu3VDkP6GxKLbtE0qviY,13234
 mcpprobe/redact.py,sha256=8VhTwssMnU2cKKL2dm2omLfjpxDWtX1GJTS8f_iWcTM,3775
-mcpprobe/scanner.py,sha256=CHXVDijzpjgAyhxQYo6msIrLxVvCwgt9Ybveg-TNNkw,15561
+mcpprobe/scanner.py,sha256=ERgUL1JUW36q1toagFBAbVqO-TFTZrHAVXpjnD192kM,15854
 mcpprobe/checks/__init__.py,sha256=GR0Hu_enDizBqZYdZZhYVytHSxfMCkliqPABNV2aBz0,3459
 mcpprobe/checks/_util.py,sha256=5_8aLzoU3yfqWz6HcaHweb_j9KxuO0WgRDBiox39GIQ,3125
 mcpprobe/checks/active_stubs.py,sha256=zI-0sw2ncmg6B2tiia0laJOPcfzMFWfagY0G6wfPMfY,9129
-mcpprobe/checks/auth.py,sha256=-RaD21lILpHyv2wbw4G7RNin3u2NqQskmmh8ScS68uQ,35638
-mcpprobe/checks/base.py,sha256=iw3hAdCE-n7In6GQTtoCFWMMnORo6vA6ncz5z1kMwWc,10872
-mcpprobe/checks/baseline.py,sha256=Wm4rsxFg8ZLy_pFD1IiN02lt1pbLTyVFtnZWMftpyOU,11475
+mcpprobe/checks/auth.py,sha256=io9T2smWBCHSzTjRMr6TNmnLl7hlUaqf1D2RmLxKT6Q,35946
+mcpprobe/checks/base.py,sha256=GjMGJbXSNXibZUkv8k0E3CBfvpHaAwjVOp18O96HK1o,11124
+mcpprobe/checks/baseline.py,sha256=cyNDmCYBgxLnA3Z3IloY4sA369965qMNqWlnv5ZBO_M,11514
 mcpprobe/checks/capability.py,sha256=3-BQolVRCEnz1ik27I07-05J5Pb2dcojg3DfD4H1k7M,13506
-mcpprobe/checks/metadata.py,sha256=oXRwnE0itYMpkW0gzCELPCjG9RPVd4e0NMtuhvXDQsU,25870
+mcpprobe/checks/metadata.py,sha256=I83VA_RH_UNxMIjmSq8WxbuH5JLho0IzsLjYLyhqW_o,25960
 mcpprobe/checks/poisoning.py,sha256=oaZrKG_QJWBr0dtOiKsxD2OdkbeMNwuuavNaLc7MJ5g,31915
 mcpprobe/checks/proof.py,sha256=0h4uDF5AvKpkEWRAVtNk9I0Ei5fUugeqRqiNf3Ln1aA,6091
 mcpprobe/checks/protocol_2026.py,sha256=PEWu61h8s718WQf62O6rEii_qTLeP60tC2lA0TiAU5M,35456
-mcpprobe/checks/robustness.py,sha256=mMIl43tP-d-WkJmIJ501qHOLiwCC-IVjzjPNNDGS164,18215
+mcpprobe/checks/robustness.py,sha256=TLL03Dp6wAYRfCvpK5dPahWU1YSX_Vx6M7vQeCR55pM,18310
 mcpprobe/checks/tool_surface.py,sha256=nbHiaM-LoDoK5y0hCo2mMeZUHR2UegXfUtjvjd4zjzQ,16660
-mcpprobe/checks/transport_conformance.py,sha256=rZ0pHC2KsNoyZaJSaDnSeu4vS3qk7evWRtFl4q4tWvY,30703
+mcpprobe/checks/transport_conformance.py,sha256=kjNR8-S7n273ESjE3p1SJmaG09glnMtvMzKxOfI0bpI,30878
 mcpprobe/judges/__init__.py,sha256=W-rRq00lnOEiVIH27pAmLK52AVIRSUhRxth3dlZw_Ws,1372
 mcpprobe/judges/hf.py,sha256=lQaMq5qwrdIzivcnrdmMd9sTtHOSNEtoAxguDoMhLMI,5412
 mcpprobe/registry/__init__.py,sha256=Ou7Fy9kZUQgWYKCudnzXPit3Hi5_-RMNham3M_YhJok,1405
@@ -52,9 +52,9 @@ mcpprobe/transport/fingerprint.py,sha256=NdJ0AyQWMPzzLA0T4bRdmdgPocHdJyBPE6Pin0q
 mcpprobe/transport/http.py,sha256=apclGNB6eeIqrvk1KreweA2g6WAo3vq7jpFCpUq-LlQ,17624
 mcpprobe/transport/ratelimit.py,sha256=g6mLxbVyXVVk0ndJ2jwJuC_RqfojbyHlABUTL7ys_9w,1578
 mcpprobe/transport/stdio.py,sha256=b_7cLDTidW5HVK_p7mT1fz0uYAdA7hh5ZlmFG65EBf4,7559
-mcpprobe_scanner-0.3.2.dist-info/METADATA,sha256=CIGoEp5dEOdOJKsGqf4tonwlfB0xbbpa3DquD3oDFkM,14284
-mcpprobe_scanner-0.3.2.dist-info/WHEEL,sha256=2iZrJkDIkeDh0k9SikKMqFuRP-ua6mb4Ir1AsER4BEw,87
-mcpprobe_scanner-0.3.2.dist-info/entry_points.txt,sha256=NEMxBH370sFz_Vw8812R7adD_DDQ3ZI7ixcuWZNQCHY,47
-mcpprobe_scanner-0.3.2.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mcpprobe_scanner-0.3.2.dist-info/licenses/NOTICE,sha256=WJJBETgUGNWnB0pvAWlb0Jx42dRffM3WAtKuabvNF2o,406
-mcpprobe_scanner-0.3.2.dist-info/RECORD,,
+mcpprobe_scanner-0.3.3.dist-info/METADATA,sha256=iEqFaZ8EqmSS9M9MZv8tUJtqUPIm9Hoko3fLZDndTzE,14284
+mcpprobe_scanner-0.3.3.dist-info/WHEEL,sha256=2iZrJkDIkeDh0k9SikKMqFuRP-ua6mb4Ir1AsER4BEw,87
+mcpprobe_scanner-0.3.3.dist-info/entry_points.txt,sha256=NEMxBH370sFz_Vw8812R7adD_DDQ3ZI7ixcuWZNQCHY,47
+mcpprobe_scanner-0.3.3.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mcpprobe_scanner-0.3.3.dist-info/licenses/NOTICE,sha256=WJJBETgUGNWnB0pvAWlb0Jx42dRffM3WAtKuabvNF2o,406
+mcpprobe_scanner-0.3.3.dist-info/RECORD,,