Mcpflare MCP Server
mcpflare
npm
v1.3.7
Source verified
Published by forgedapps — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Conditional behavior directive MTC-INJ-SEQ-2 | injection |
2. Client adoption risk — 99 − 6 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| ✓ | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source |
| ✓ | inspection depth (source) — how much of the target the scan could see |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 9
high Sensitive-source and external-sink co-existMTC-FLOW-004
Tools that read sensitive data ([import_configs]) and tools that can send data out ([connect]) are exposed together. An agent can move private data to the sink.
Fix: Keep secret-reading and egress capabilities on separate, separately-approved servers.
high Tool "connect" exposes command/code executionMTC-CAP-001
Tool "connect" appears to run shell commands or evaluate code (parameter "command"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool connect
high Dynamic code execution in server code (dist/server/worker-manager.js)MTC-SRC-001
In the server's implementation (`dist/server/worker-manager.js:1066`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: eval(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/server/worker-manager.js
high Shell/command execution in server code (dist/server/worker-manager.js)MTC-SRC-002
In the server's implementation (`dist/server/worker-manager.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: child_process
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/server/worker-manager.js
high Shell/command execution in server code (dist/utils/token-calculator.js)MTC-SRC-002
In the server's implementation (`dist/utils/token-calculator.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: child_process
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/utils/token-calculator.js
medium Unconstrained command parameter "command" on "connect"MTC-CAP-006
Tool "connect" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool connect · inputSchema.properties.command
low Mutating tool "connect" declares no destructiveHintMTC-CAP-005
Tool "connect" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool connect
low Conditional behavior directiveMTC-INJ-SEQ-2
Conditional behavior directive detected in the description of tool "list_available_mcps". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.
Evidence: when call
Fix: Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.
Location: tool list_available_mcps · description
low Unconstrained path parameter "cursor_config_path" on "import_configs"MTC-CAP-008
Tool "import_configs" takes a path parameter "cursor_config_path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool import_configs · inputSchema.properties.cursor_config_path
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (10 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.3.7 latest |
A 93/100 | 9 | 1.7.0 | 2026-07-23 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan mcpflare --onlineMore in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Agent MCP server.
Security scan results for the Agent Recorder MCP server.