Loading the registry…
Sentry MCP Server
The publisher performed an authenticated act of publication — proving control of a namespace in the official MCP registry, or appearing in a first-party catalogue an operator curates. That establishes WHO published it. It is not a security finding, and attested artifacts carry Flagged verdicts too.
101 critical findings reported by cisco-skill-scanner, agent-audit-kit, 70 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 3 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/getsentry/sentry-mcp, 1114 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- sentry-mcp
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
Incomplete run
0 findings · 1.0s
v2.0.11
947 findings · 24.4s
v0.3.74
161 findings · 21.6s
v0.1.0
6 findings · 28.8s
v0.1.0
0 findings · 28.9s
v0.1.0
0 findings · 40.8s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
8 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 1, 2026 | Scan Halted | — | agentshield ·!: incompletecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | rejected |
| Aug 2, 2026 | Scan Halted | — | agentshield ·!: incompletecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 21, 2026 | Scan Halted | — | agentshield ·!: incompletecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: complete | rejected |
| Jul 20, 2026 | Scan Halted | — | agentshield ·!: incompletecisco-skill-scanner: completeagent-audit-kit: complete | rejected |
| Jul 20, 2026 | Scan Halted | Clean → Flagged | agentshield ·!: incompletecisco-skill-scanner: completeagent-audit-kit: complete | rejected |
| Jul 20, 2026 | Clean100 | — | agentshield ·n/a: not applicablecisco-skill-scanner ·n/a: not applicableagent-audit-kit: completetrivy: completeosv-scanner ·n/a: not applicable | completed |
| Jul 20, 2026 | Clean100 | — | agentshield ·n/a: not applicablecisco-skill-scanner ·n/a: not applicableagent-audit-kit: completetrivy: completeosv-scanner ·n/a: not applicable | completed |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 1,114 findings across every scanner that examined this package. 13 of 101 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 65 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
834 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: AAK-SECRET-002, COMMAND_INJECTION_EVAL, AAK-OAUTH-001 and 10 more · Files: packages/mcp-core/src/telem/sentry.test.ts, /repo/packages/mcp-cloudflare/src/test-utils/ajv-stub.ts, packages/smoke-tests/src/smoke.test.ts and 72 more · reported by agent-audit-kit, cisco-skill-scanner
20 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/docs/SKILL.md, /repo/docs/releases/SKILL.md, /repo/docs/cloudflare/SKILL.md and 7 more · reported by cisco-skill-scanner
4 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/deploy.yml, .github/workflows/release.yml, .github/workflows/token-cost.yml and 1 more · reported by agent-audit-kit
The model could have called any of these a false positive and did not.
51 AAK-INDIA-PII-001
Files: packages/mcp-cloudflare/src/client/components/ui/icons/gemini.tsx · reported by agent-audit-kit
35 DATA_EXFIL_JS_NETWORK
Files: /repo/packages/mcp-cloudflare/src/client/contexts/auth-context.tsx, /repo/packages/mcp-cloudflare/src/client/hooks/use-mcp-metadata.ts, /repo/packages/mcp-cloudflare/src/server/index.ts and 12 more · reported by cisco-skill-scanner
15 AAK-OAUTH-007
Files: packages/mcp-cloudflare/src/server/metrics.ts, packages/mcp-cloudflare/src/server/index.ts, packages/mcp-cloudflare/src/server/oauth/constants.ts and 12 more · reported by agent-audit-kit
14 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/packages/mcp-core/scripts/generate-definitions.ts, /repo/packages/mcp-core/scripts/measure-token-cost.ts, /repo/packages/mcp-server/src/auth/token-cache.ts and 1 more · reported by cisco-skill-scanner
8 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/packages/mcp-server-evals/SKILL.md, /repo/packages/mcp-test-client/SKILL.md and 5 more · reported by cisco-skill-scanner
57 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: YARA_credential_harvesting_generic, AAK-TRUST-006, HIDDEN_DATA_FILE and 3 more · Files: /repo/packages/mcp-core/src/telem/sentry.test.ts, .claude/settings.json, /repo/packages/mcp-test-client/.env.test and 28 more · reported by cisco-skill-scanner, agent-audit-kit
8 The model's answer was not one of the permitted verdicts.
Rules: AAK-SEC-MD-001, HIDDEN_DATA_FILE · Files: SECURITY.md, /repo/.agents/skills/mcp-audit/SKILL.md, /repo/.agents/skills/mcp-audit/references/spec-baseline.md and 5 more · reported by agent-audit-kit, cisco-skill-scanner
Critical findings indicate potential for data exposure and command execution.
The artifact contains multiple critical findings, including potential for credential harvesting, command injection via `eval`, and exposure of sensitive PII within `packages/mcp-cloudflare/src/client/components/ui/icons/gemini.tsx`. It also exhibits capabilities for network egress of secrets and potential for SQL injection. These issues suggest the artifact could perform unauthorized operations or expose confidential information.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
Files: .mcp.json, .cursor/mcp.json, plugins/sentry-mcp-experimental/mcp.json and 1 more · reported by agent-audit-kit
6 AAK-MCP-ATTEST-001
Files: .mcp.json, .cursor/mcp.json, plugins/sentry-mcp-experimental/mcp.json and 1 more · reported by agent-audit-kit
6 COMMAND_INJECTION_EVAL
Files: /repo/packages/mcp-cloudflare/worker-configuration.d.ts, /repo/packages/mcp-server/src/auth/device-code-flow.ts · reported by cisco-skill-scanner
6 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/packages/mcp-cloudflare/src/server/oauth/helpers.ts, /repo/packages/mcp-cloudflare/src/server/routes/chat-oauth.ts, /repo/packages/mcp-cloudflare/src/server/routes/chat.ts and 3 more · reported by nerlo-behavioral
5 LOW_ANALYZABILITY
Files: /repo, /repo/packages/mcp-core/src/tools/support/search-issues, /repo/packages/mcp-core and 2 more · reported by cisco-skill-scanner
4 AAK-MARKETPLACE-001
Files: .cursor-plugin/marketplace.json, .claude-plugin/marketplace.json · reported by agent-audit-kit
3 AAK-DNS-REBIND-001
Files: packages/mcp-cloudflare/src/server/routes/metadata.ts, packages/mcp-cloudflare/src/server/routes/chat.ts, packages/mcp-test-client/src/mcp-test-client-remote.ts · reported by agent-audit-kit
3 AAK-LEGAL-002
Files: packages/smoke-tests/package.json, packages/mcp-test-client/package.json, packages/mcp-server-tsconfig/package.json · reported by agent-audit-kit
3 AAK-LLM-SQL-RCE-001
Files: packages/mcp-server-evals/src/bin/start-mock-stdio.ts, packages/mcp-server/src/cli/resolve.ts, packages/mcp-server/src/cli/usage.ts · reported by agent-audit-kit
3 AAK-MCP-018
Files: packages/mcp-test-client/src/auth/oauth.ts, packages/mcp-server/src/transports/stdio.ts, packages/mcp-core/src/server.ts · reported by agent-audit-kit
3 AAK-OAUTH-005
Files: packages/mcp-cloudflare/src/server/index.ts, packages/mcp-cloudflare/src/server/lib/mcp-handler.ts, packages/mcp-core/src/api-client/client.ts · reported by agent-audit-kit
3 AAK-OAUTH-006
Files: packages/mcp-cloudflare/src/server/oauth/index.ts, packages/mcp-cloudflare/src/server/routes/chat-oauth.ts, packages/mcp-test-client/src/auth/oauth.ts · reported by agent-audit-kit
2 AAK-MCP-009
Files: .mcp.json, .cursor/mcp.json · reported by agent-audit-kit
2 AAK-OAUTH-008
Files: packages/mcp-cloudflare/src/server/oauth/telemetry.ts, packages/mcp-cloudflare/src/server/lib/mcp-handler.ts · reported by agent-audit-kit
2 EXCESSIVE_FILE_COUNT
Files: /repo/packages/mcp-core/., /repo/. · reported by cisco-skill-scanner
2 HIDDEN_DATA_FILE
Files: /repo/openspec/changes/refine-project-management-tools/.openspec.yaml · reported by cisco-skill-scanner
2 YARA_prompt_injection_unicode_steganography
Files: /repo/packages/mcp-cloudflare/public/keycap-v.png · reported by cisco-skill-scanner
1 AAK-MCP-SDK-CVE-2026-52869-001
Files: pnpm-lock.yaml · reported by agent-audit-kit
1 AAK-OAUTH-001
Files: packages/mcp-cloudflare/src/server/authorization-server-metadata.ts · reported by agent-audit-kit
1 AAK-SECRET-004
Files: packages/mcp-core/src/tools/catalog/search-events.ts · reported by agent-audit-kit
1 AAK-SUPPLY-003
Files: package.json · reported by agent-audit-kit
1 AAK-TRUST-001
Files: .claude/settings.json · reported by agent-audit-kit
1 AAK-TRUST-004
Files: .claude/settings.json · reported by agent-audit-kit
1 OVERSIZED_FILE
Files: /repo/packages/mcp-cloudflare/public/demo.cast · reported by cisco-skill-scanner
Showing 25 of 104; the rest are in the per-scanner reports above.