MCP Inspector
Visual testing tool for MCP servers
Is MCP Inspector safe? Strong public trust posture, backed by multiple independent signals.
Compare MCP Inspector
How does it stack up against its Protocols & Tool Integration neighbours?
Pick any agent to compare →In detail: MCP Inspector scores 91.7/100 (Grade A), ranked #11 of 1371 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 7.3/10; 32% of recent commits are signed; no published advisory affects its latest release (@modelcontextprotocol/inspector); last pushed 2026-10-13. Every point is earned from checkable signals — never paid placement. How scoring works →
How MCP Inspector could raise its score
Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.
- Raise the OSSF Scorecard from 7.3 to 9.0lowest checks: CII-Best-Practices 0, Code-Review 0, Fuzzing 0 +2.5 → 94.2 A · #2 of 62
- Sign every commit32% signed today +2.3 → 94.0 A · #2 of 62
Chain of custody
Scanners check what the code says. This traces who ships MCP Inspector and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.
-
Source Partly signed
github.com/modelcontextprotocol/inspector, NOASSERTION, last pushed 2026-10-13. 32% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.
-
Review and release Strong
OpenSSF Scorecard rates the repository's practices 7.3/10 (scanned Oct 10, 2026). The checks that decide who can get a change released:
- Code Review0
- Branch Protection5
- Signed Releasesn/a
- Dangerous Workflow10
- Token Permissions10
- Pinned Dependencies4
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 5CI-Tests 10CII-Best-Practices 0Code-Review 0Contributors 10Dangerous-Workflow 10Dependency-Update-Tool 10Fuzzing 0License 9Maintained 10Packaging 10Pinned-Dependencies 4SAST 2Security-Policy 10Signed-Releases -1Token-Permissions 10Vulnerabilities 10 -
Published packages Linked and attested
- npm @modelcontextprotocol/inspector Source link points back to this repo Build provenance attested
-
What you install today No known advisories
Latest release checked: @modelcontextprotocol/inspector 2.10.1. No published advisory affects it (OSV, checked 2026-10-13).
Changes to this chain
- 2026-09-23 License classification changed from unlicensed to open
- 2026-07-29 License classification changed from open to unlicensed
Evidence behind this score
Coverage B: 3 of 5 independent evidence types found.
- GitHub repository data
- Package downloads
- Supply-chain checks
- Public actions (missing)
- Community mentions (missing)
Verify this score yourself
Every build re-issues MCP Inspector’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.
What this score doesn’t check
It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.
How MCP Inspector compares in Protocols & Tool Integration
- #1 MCP TypeScript SDK 94.6 +2.9
- #2 MCP Python SDK 93.9 +2.2
- #3 MCP Inspector 91.7 this agent
- #4 A2A / Agent2Agent Protocol 89.4 −2.3
- #5 FastMCP (TypeScript) 86.8 −4.9
Bars show each HVTrust score; the tick marks MCP Inspector’s 91.7.
Where the 91.7 comes from
HVTrust dimensions vs the Protocols & Tool Integration average
91.7 / 100 · 100.0% confidenceMCP Inspector Protocols & Tool Integration average (62 agents)
Quick Trust Read
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade A reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →
Rank Trend
Activity & Reach
Analysis
Activity Inputs
89.1 / 100Common questions about MCP Inspector
Does MCP Inspector publish package provenance?
Does MCP Inspector have an OpenSSF Scorecard?
Is MCP Inspector actively maintained?
What license does MCP Inspector use?
Are MCP Inspector's commits signed?
Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.
Compare MCP Inspector head-to-head
AI agent surface
MCP, providers, tool surface
These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →
- MCP signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
Maintain MCP Inspector?
For maintainers
HVTrust scores MCP Inspector from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.
Reputation Timeline
Signal history
Embed Badge Badge guide for maintainers →
For maintainers
[](https://hvtracker.net/agents/mcp-inspector)
<a href="https://hvtracker.net/agents/mcp-inspector"><img src="https://hvtracker.net/badge/mcp-inspector.svg" alt="HVTrust"></a>
Other agents in Protocols & Tool Integration
GitHub REST API (repo, commits, stars, forks, license) · npm Registry (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON