Sphior AI Governance MCP server
io.github.Toraastrta/sphior-ai-governance-mcp·v0.2.1·1 starsRecord what your AI did as tamper-evident evidence for ISO 42001, EU AI Act and SOC 2. Hash-only.
1 stars53 downloads/wk
Reviews
Write oneNobody has reviewed Sphior AI Governance yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Sphior AI Governance tools (2)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
record_ai_executionRecord one AI / AI-agent execution as tamper-evident, independently verifiable evidence
record_ai_executionsRecord multiple AI executions in one call (up to 200). Same fields as record_ai_execution.
Public scan report
scanner v0.1.10 · 2026-10-27 · same rubric, same numbers if you re-run it
- Code scan15 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 1 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Sphior AI Governance compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 83/100
- higher than 65% of 48,255 servers
- Tools
- 2
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1
- more than 65% of 28,688 servers
- Downloads a week
- 53
- more than 44% of 12,191 servers with a package
What its tools let an agent do: 2 read
Install Sphior AI Governance in Claude Code, Cursor or VS Code
Runs npx -y sphior-ai-governance-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add sphior-ai-governance-mcp -- npx -y sphior-ai-governance-mcp
What the publisher says
From the Sphior AI Governance repository's README, as published. We do not edit it. Read it on GitHub
SPHIOR CODE
Deterministic secrets and insecure-pattern (CWE) detection for VS Code, JetBrains IDEs, the command line, and CI — running entirely on your machine.
No AI. No source upload. No telemetry. The same input always produces the same findings.
Try it in 10 seconds
No install, no account, no config:
npx @sphior/scan run .SPHIOR CODE: 3 findings (critical=1 high=1 medium=1 low=0) 1 files scanned
engine=0.1.0 ruleset=2026.10.20-23In a terminal you get a table sorted by severity. Piped, you get SARIF — so npx @sphior/scan run . | jq works, and --sarif out.sarif is accepted by GitHub code scanning.
Give findings to the coding assistant you already use, via MCP:
npx sphior-code-mcp # or add it from the MCP registry: io.github.Toraastrta/sphior-code-mcpEditors: VS Code · JetBrains · Open VSX
Why this exists
Most code scanners either ship your source to a server, or ask a language model what it thinks. Both make results hard to trust: you cannot reproduce them, and you cannot explain them to an auditor.
This one is deterministic. Every finding comes from a rule with a stable id, a CWE mapping, and a fingerprint derived from the code itself. Run it twice, get the same answer. Run it on someone else's machine, get the same answer.
What it finds
(AWS, GCP, GitHub, Stripe, Slack, OpenAI, Anthropic, …). Only masked previews are ever emitted; raw values never leave the process.
- Hard-coded secrets — provider signatures plus entropy checks, across 36 rules
XSS sinks, disabled TLS verification, weak crypto, unsafe deserialization, path traversal, SSRF, and more.
- Insecure code patterns mapped to CWE — 84 rules covering command injection, eval,
to sink, so db.query("… " + req.query.id) is reported as SQL injection rather than a generic string-concatenation warning.
- Data-flow (taint) analysis for JavaScript/TypeScript — tracks untrusted input from source
Languages
JavaScript, TypeScript (+ JSX/TSX), Python, Go, PHP, Ruby, Java, C#, Rust, Kotlin, C, C++, Scala, Swift — 14 languages, parsed with real grammars (tree-sitter), not regex alone.
Regex rules are used only where a parser adds nothing. When a language has an AST backend, the parser-based results take precedence and the regex equivalents are suppressed, which keeps false positives down.
Detection is regression-gated in CI against a fixed corpus: a rule change that loses a detection, or that starts firing on a known-safe variant, fails the build rather than shipping quietly.
What it does not do
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Sphior AI Governance: common questions
- Is Sphior AI Governance MCP server safe?
- Mostly: it is graded B (83/100). Read the Sphior AI Governance safety report
- How do I install Sphior AI Governance?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Sphior AI Governance need an API key?
- Yes. The registry entry asks for
SPHIOR_AIGOV_TOKEN. - Is Sphior AI Governance maintained?
- The last commit was 9 days ago (2026-10-26). The latest release is v0.2.1.
- What can I use instead of Sphior AI Governance?
- Servers from other publishers that do the same job: Tradememory Protocol MCP server.
- How does Sphior AI Governance compare with other MCP servers?
- safety score 83/100 (higher than 65% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Sphior AI Governance
Same job from other publishers: the closest match first, then the best rated.
- Tradememory ProtocolTamper-evident decision audit trail and outcome-weighted memory for AI trading agents.not reviewedEstablishedB
