CanopiiCanopiiAll serversEnterprise →

fast-agent MCP Server Security Report

evalstate/fast-agent

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

Security Trust Score
Grade B · Moderate posture
Tier 1 · Public sourceHigh confidence · 78%latest vmain@b8a36d2 Repository
Declared MCP capabilities
ToolsResourcesPrompts

Run it securely

Host evalstate/fast-agent in a governed environment — SSO in front, every tool call attributed and audited.

Are you the maintainer?

Verify with GitHub to get alerted whenever evalstate/fast-agent changes score — and claim the badge for your README.

Claim this server

The short answer

Is fast-agent safe to use?
fast-agent scores 80/100 (grade B) on the Canopii Trust Index — good, minor gaps. It passes 13 of the 21 security controls that apply to it, with no confirmed security failures.
How reliable is the security score for fast-agent?
We could evaluate 78% of the controls that apply to fast-agent. Scores are deterministic — the same source always produces the same score — and a partially-scannable server cannot present a high one, because confidence caps the result. The scanner is open source, so this score can be reproduced independently.
How was fast-agent scored?
Its published source was scanned against a fixed catalog of weighted security controls covering code safety, committed secrets, dependency vulnerabilities, tool-description integrity, authentication and transport, and maintenance. A confirmed flaw caps the score outright regardless of what else passes. The full rubric is published.
Reputation4.0kstars460forks43open issuestodaylast commit2yage

Security controlslatest scored version vmain@b8a36d2

Each control is evaluated deterministically with evidence. The score is earned from passing controls; a failed guard caps it.

Model–MCP Runtime Guardrails

  • Pass
    Strict JSON Schema EnforcementadditionalProperties:false present

    Tool inputs are constrained (additionalProperties:false), so unexpected arguments can't be smuggled in.

  • Pass
    In-Session Definition Integrityguardno call-gated or call-time tool definition changes

    Tool and prompt definitions stay fixed during a session — they don't change after a few calls, which is how runtime-gated rug-pulls slip past one-time review.

  • Not checked
    Indirect Prompt Injection (IPI) Defensesguardno tools extracted

    Tool/prompt/resource text is free of hidden instructions that could hijack the agent.

  • Not checked
    User-in-the-Loop / Approval Scopeguardno tools extracted

    No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval.

  • N/A
    Tool Definition Integrityguardno prior version to diff

    Every consecutive version pair is diffed for new injection markers or destructive scope — a risky diff anywhere in history is a rug-pull (fail, durable); benign description drift warns.

Application Security Checks

  • Warn
    No path traversalguard2 occurrences

    Naive path checks let tools read/write outside intended directories (EscapeRoute-class).

    design/fast-agent-system/_ds_bundle.js:2383design/fast-agent-system/ui_kits/website/Shell.jsx:38

    Fix: Resolve to a canonical path and verify containment; reject ../ and symlinks.

  • Warn
    Dependencies pinned (lockfile)no lockfile found

    A lockfile makes installs reproducible and resistant to silent dependency swaps.

    Fix: Commit a lockfile (package-lock.json / pnpm-lock.yaml / poetry.lock).

  • Warn
    Has a security policyno security policy

    A SECURITY.md gives a private path to report vulnerabilities.

    Fix: Add SECURITY.md with a disclosure contact and process.

  • Pass
    No command-injection sinksguardno sinks found

    Untrusted tool input reaching a shell yields remote code execution.

  • Pass
    No dynamic code executionguardno sinks found

    eval()/exec()/Function() on tool-derived strings allows arbitrary code execution.

  • Pass
    No SSRF sinksguardno sinks found

    Fetching tool-supplied URLs can pivot into internal networks and metadata services.

  • Pass
    No unsafe deserializationguardno sinks found

    pickle/yaml.load/etc. on untrusted data can execute code.

  • Pass
    No committed secretsguardno secrets found

    Hardcoded keys/tokens in published source are live credentials an attacker can use.

  • Pass
    Credentials sourced from environmentreads credentials from environment

    Reading secrets from env/secret stores avoids hardcoding them.

  • Pass
    Actively maintainedrecent commits

    Unmaintained servers don't receive security fixes.

  • Pass
    Repository not archivedguardactive

    Archived repositories will never be patched.

  • Pass
    Declares a licenseApache-2.0

    A clear license is required for legal enterprise use.

  • Pass
    Adoption & popularityestablished adoption

    A small, capped nudge from stars/downloads — widely-used servers get more eyes on bugs. It can never offset a real security failure.

  • Not checked
    No known-vulnerable dependenciesno lockfile found

    Runtime dependencies (parsed from the lockfile) are scanned against OSV.dev for published CVEs. Advisory: flagged dependencies lower the score but don't hard-cap it, since transitive reachability is unproven.

  • Not checked
    Signed releasesnot evaluated

    Signed releases let consumers verify artifacts weren't tampered with.

  • N/A
    No install/post-install scriptsguardno published package

    install hooks run arbitrary code on every consumer at install time.

  • N/A
    Package name not typosquattingguardno published package

    Names mimicking popular packages are a common malware delivery vector.

  • N/A
    Published with provenanceno published package

    Build provenance attests the artifact was built from the claimed source by CI.

  • N/A
    Established maintainerno published package

    Brand-new / single anonymous maintainers raise takeover and malware risk.

Transport & Trust Model

  • Warn
    Execution Sandboxingruns natively (no container image)

    A container/sandbox image limits blast radius; a server that runs natively has full host access.

    Fix: Ship a Dockerfile/Containerfile (or document a sandboxed run) so the server runs isolated.

  • Pass
    Network Exposureno bind-all detected

    Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.

  • N/A
    Transport Encryption (TLS)guardno remote endpoints

    Plaintext HTTP exposes traffic and bearer tokens to interception.

  • N/A
    IAM / Authentication Scopingno remote endpoints

    OAuth 2.1 / Protected Resource Metadata gates who can invoke tools.

  • N/A
    No Token Passthroughguardno HTTP transport

    The client's token is never forwarded to downstream APIs — the server obtains its own, correctly-scoped credential instead.

  • N/A
    DNS-Rebinding Protectionno HTTP transport

    HTTP endpoints reject requests carrying an unlisted Origin, so a malicious web page can't drive the server through the user's browser.

  • N/A
    Live Endpoint Reachablenot dynamically scanned

    A dynamic scan connected to the declared remote endpoint and it responded — verified live, not a dead URL.

  • N/A
    Authentication Enforced (live)not dynamically scanned

    If the server declares auth is required, it must actually reject anonymous clients. Serving tools to unauthenticated callers is a real exposure.

Embed this score

Add the live badge to your README — it updates automatically on every rescan.

Canopii Trust Score badge preview
markdown[![Canopii Trust Score](https://index.canopii.dev/api/badge/evalstate/fast-agent)](https://index.canopii.dev/server/evalstate/fast-agent)
html<a href="https://index.canopii.dev/server/evalstate/fast-agent"><img src="https://index.canopii.dev/api/badge/evalstate/fast-agent" alt="Canopii Trust Score" /></a>

Versions

VersionScoreStatus
vmain@b8a36d2latest80Bscored
vmain@337c59880Bscored
vmain@a8f992c80Bscored
vmain@31c5e2980Bscored
vmain@3d0325e80Bscored
vmain@3d77d7880Bscored
vmain@cc222a380Bscored
vmain@56f22c380Bscored
vmain@18eb91f80Bscored
vmain@5c4453b80Bscored
vmain@6d9f93b80Bscored
vmain@819c0de80Bscored
vmain@5d6e5b680Bscored
vmain@470f95e80Bscored
vmain@cc9f2dd80Bscored
vmain@9ab215f80Bscored
vmain@73455c380Bscored
vmain@9574ab592Ascored
vmain@90298d692Ascored
vmain@e8fd01092Ascored
vmain@4134c9883Bscored
vmain@5e3ad9a83Bscored
vmain@b6d9da682Bscored
vmain@d59610083Bscored
vmain@07c460e83Bscored
vmain@920cb6783Bscored
vmain@2fc269983Bscored
vmain@0cb9cd983Bscored
vmain@96ded6683Bscored
vmain@fbb9b1483Bscored
vmain@905eb6c83Bscored
vmain@bb6041d83Bscored
vmain@9e4685583Bscored
vmain@866fb5383Bscored
vmain@3342d5883Bscored
vmain@9af257683Bscored
vmain@bc2ce5783Bscored
vmain@e05669483Bscored
vmain@9be516983Bscored
vmain@3d552fd83Bscored
vmain@c2389c283Bscored
vmain@f6ad77383Bscored
vmain@1b58e6883Bscored
vmain@c14a5ab83Bscored
vmain@610a2f583Bscored
vmain@c28bbce83Bscored
vmain@b736f4815Fscored
vmain@4ce141883Bscored
vmain@0b8a36415Fscored
vmain@86ffa5383Bscored
vmain@64eec1b83Bscored
vmain@f2b69c382Bscored

Wondering how this compares? The MCP Security Index tracks grade distribution, committed secrets, and missing authentication across the whole ecosystem, refreshed monthly.