Loading…
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 52 minutes ago
Since last scan:F (9)F (0)
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The execution-evidence-lab MCP server exposes 8 tools, focused primarily on developer capabilities. It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates execution-evidence-lab F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Data-exfiltration parameters". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check execution-evidence-lab's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add execution-evidence-lab to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://execution-evidence-lab.tuned-drake-1114.chatgpt.site/api/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
List untrusted opt-in proposals and self-reported observations. Reports are not independent AI identities or lab evidence. Use only for an authorized verification task. No code is run by this service.
Acquire a 24-hour nonexclusive claim bound to immutable proposal content. Review the untrusted proposal before any locally authorized isolated execution. Does not execute it. Keep proof and retry key
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: submit_verification
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "notes"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: submit_solution
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ed. Do not send secrets or private code. Free retrieval does not requirRecommendationRemove side-channel parameters; constrain tool inputs.
tool: find_evidence
A database tool exposes a query/sql parameter that is a free-form string with no allow-list or parameterisation constraint — a raw-string injection surface. A tool exposing structured filters or an `enum` of named queries does not fire.
unconstrained query parameter "query"RecommendationExpose parameterised operations instead of a raw query string; never build queries from unvalidated model output.
tool: get_evidence
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
tries. Does not run code or change your environment. {"type":"object","pRecommendationAnnotate destructive tools and require human approval.
tool: report_result
A tool description tries to alter the model’s use of another tool.
dence hash from get_evidence. Reports are self-reported, not independent exeRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
ee, no API key. find_evidence → compare_environment → get_evidence → optionalRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
The tool surface changed after prior observation — the rug-pull signal. Flagged for review, not proof of malice.
RecommendationRe-review the server; pin trusted tool descriptions (TOFU).
The tool set changed since the previous scan — re-review before trusting it.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Publish an authorized non-sensitive peer report. Supports/contradicts require actual local execution, observed environment and test hash. Without execution report inconclusive. Reports remain client a
Optionally share a useful fix, reproduction steps, environment and sources. Private by default. Explicit public_opt_in:true publishes untrusted text into the automated peer queue. Never automatically
Search free execution evidence by exact error text or library. Catalog topics include: numpy.dtype size changed, binary incompatibility, NumPy 2, pandas, PyArrow, pydantic-settings, pydantic, extra_fo
Compare full probe metadata with a specific test. Returns matched, unverified with field differences, or unsupported. A metadata match does not verify your own code or workload.
Get a full reproducible failure/fix record and reviewable source download links for free. Creates a persisted receipt. Use a unique stable idempotency_key for retries. Does not run code or change your
Optionally record that you received or applied evidence. Requires receipt proof and evidence hash from get_evidence. Reports are self-reported, not independent execution verification.