Cloudflare Docs MCP
https://docs.mcp.cloudflare.com/mcp
github.com/cloudflare/mcp-server-cloudflare
Severity breakdown
Worst finding
Tool `search_cloudflare_documentation` accepts unconstrained string input
· search_cloudflare_documentation
The following string parameter(s) have no `maxLength` constraint: `query`. Unbounded strings let an attacker stuff arbitrary payloads through the tool, including indirect-injection content.
fix: Add a `maxLength` to each string property, or constrain with an `enum` or `pattern`. Most legitimate tool inputs fit under a few hundred bytes.
All 2 findings
- mediumTool `search_cloudflare_documentation` accepts unconstrained string input· search_cloudflare_documentationunconstrained input
The following string parameter(s) have no `maxLength` constraint: `query`. Unbounded strings let an attacker stuff arbitrary payloads through the tool, including indirect-injection content.
fix: Add a `maxLength` to each string property, or constrain with an `enum` or `pattern`. Most legitimate tool inputs fit under a few hundred bytes.
- mediumTool `search_cloudflare_documentation` description mentions money but no `money` side-effect is declared· search_cloudflare_documentationexcessive agency
Description: "Search the Cloudflare documentation. This tool should be used to answer any question about Cloudflare products or features, including: - Workers, Pages, R2, Images, Stream, D1, Durable Objects, KV, Workflows, Hyperdrive, Queues - AI Search, Workers AI, Vectorize, AI Gateway, Browser Run - Zero Trust, Access, Tunnel, Gateway, Browser Isolation, WARP, DDOS, Magic Transit, Magic WAN - CDN, Cache, DNS, Zaraz, Argo, Rulesets, Terraform, Account and Billing Results are returned as semantically similar chunks to the query. " -- this references money/payment/refund/etc., but the declared side_effects ([]) don't include `money`. A capframe-bind policy that relies on declared side_effects to scope spend caveats will under-scope this tool.
fix: Add `money` to the tool's `side_effects` declaration, or rewrite the description to clarify that no actual money moves.
Reproduce this
Every finding above comes from a public, deterministic rule engine — no LLM in the decision path, same input always the same output. You can run it against this server yourself and get byte-identical results:
curl -fsSL capframe.ai/install | sh capframe find ./your-mcp-config.json --out findings.json
Five-step quickstart if you want the whole Find → Bind → Guard loop. If you'd rather have someone read your real tool definitions rather than the advertised surface — including the ones this public scan can't reach — that's the Agent Security Audit.
How this was scored
Source http — live HTTP MCP endpoint, classified against every rule. Findings are emitted by the public capframe.findings.v1 schema. Score = 100 − (10·Critical + 4·High + 2·Medium + 1·Low), clamped to [0, 100].
Disagree with a finding? Open an issue.