cd /news/ai-agents/saktum-check-test-mcp-servers-agains… · home › topics › ai-agents › article
[ARTICLE · art-174240] src=github.com ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

Saktum Check – test MCP servers against the OWASP MCP Top in one command

Saktum released Saktum Check, an early-release command-line tool that tests MCP servers against the OWASP MCP Top 10, grading conformance, sign-in, security, agent experience and performance and returning a signed, verifiable report. The tool runs locally with nothing uploaded and was validated on 31 public MCP servers before release; it reports findings such as an AWS access key exposed in a tool definition and a JavaScript stack trace leaked in an error, and estimates that agents spend about 142 tokens reading a server's tools each turn, about $0.43 per 1,000 turns. Saktum plans active checks for servers you own, sign-in registration and redirect checks, a lock file that catches silent tool changes, a sandbox for untrusted servers, and CI integration via GitHub Action and SARIF in January, with feedback shaping v0.2.

key takeaway

Running `npx saktum check` against an MCP server grades it against the OWASP MCP Top 10 and flags issues like an AWS access key in a tool schema or a stack trace in an unknown-tool error, with `--fail-on high` setting a CI exit code.

read3 min views1 publishedNov 22, 2026
Saktum Check – test MCP servers against the OWASP MCP Top in one command
Image: Michielbdejong (auto-discovered)

Test your MCP server in one command: conformance, sign-in, security mapped to the OWASP MCP Top 10, agent experience, what your tools cost an agent in context, and performance. A grade, plain findings, a fix for each, and a signed result anyone can verify.

npx saktum check -- npx -y @your/mcp-server          # a local server
npx saktum check https://your-server.example/mcp     # a remote server (sign-in checks run without a token)

Runs on your machine. Nothing is uploaded. Your own environment variables are never passed to the server.

  GRADE F  (trust score 49, capped: a critical check failed)
  Grade F: 2 problems found (1 critical, 1 medium); 11 checks passed.
  Fix first (critical): found what looks like an AWS access key in tool upload_report.
  Agents spend about 142 tokens reading these tools on every turn, about $0.43 per 1,000 turns.

  agent-experience   100
  conformance        100
  security            61

✗ FAIL CRITICAL sec.secrets.exposed  No secrets in tool definitions or responses
    Found what looks like an AWS access key in tool upload_report. Anyone who can list tools or trigger an error can read it.
    Evidence: ess_key_id":{"type":"string","default":"AKIA…[redacted 16 chars]"}},"required":["nam
    Fix: Remove keys, tokens and passwords from descriptions, schemas, defaults, examples and error messages; load them from a secret store at runtime.
✗ FAIL MEDIUM sec.errors.leakage  Errors do not expose internals
    The error for an unknown tool exposes a JavaScript stack trace, which helps attackers map your internals.
    Evidence:     at handleCall (/home/deploy/acme-mcp/src/handlers.js:42:11)

Every report ends with OWASP MCP Top 10 coverage: which categories this run tested and which come in later releases.

Area Checks
Conformance Handshake, tool list, valid input schemas (draft-07, 2019-09, 2020-12), tool names, unknown-tool handling
Sign-in (remote servers) HTTPS; 401 with a Bearer challenge pointing to resource metadata (RFC 9728); protected resource metadata; authorization server metadata with PKCE S256 (RFC 8414, RFC 7636); invalid tokens rejected (RFC 6750)
Security Hidden instructions to the agent, invisible and bidirectional characters, terminal escape sequences, secrets in tools or errors (always redacted), stack traces and source paths in errors
Agent experience Danger annotations, description quality, context cost in tokens and dollars
Performance (never scored) Start-up, latency, memory of the whole process tree, and a rate-limit burst test with --active

Validated on 31 public MCP servers before release. Each check cites the specification clause or OWASP item it verifies.

Option Use
--env NAME=VALUE Give a local server what it needs to start (repeatable)
--header "Authorization: Bearer <token>" Test a remote server's tools, not just its sign-in
--html report.html Also write an HTML report
--fail-on high Exit code for CI: fail on findings at or above this severity
--price-per-mtok 3 Your model's input price, for the cost estimate
--active Extra checks that send more traffic. Only against servers you own.

npx saktum doctor -- <same target> explains why a server will not start or connect. npx saktum verify saktum-report.json checks a signed result.

This is an early release, and feedback shapes v0.2. In two minutes:

Planned next: active checks for servers you own, sign-in registration and redirect checks, a lock file that catches silent tool changes, a sandbox for untrusted servers, then CI (GitHub Action, SARIF) in January.

Results are self-tested (assurance level L1): the signature proves the report was not changed after the run, not that it was run independently. Findings describe the server at the time of the run and are not a guarantee of security. Static checks can miss cleverly disguised attacks; a pass is evidence, not proof.

Apache-2.0. Security issues: see SECURITY.md.

── more in #ai-agents 4 stories · sorted by recency
── more on @saktum 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/saktum-check-test-mc…] indexed:0 read:3min 2026-11-22 · —