MCP server · trust report

dev.agentsim/mcp

3 checks that ran failed — supply chain, version behavior and transport config — so this release can’t be trusted as-is.

Publisher
dev.agentsim
Repository
github.com/agentsimdev/agentsim-mcp
Install
pypi:agentsim-mcp, pypi:agentsim-mcp
Versions
25
MCP revision
2025-11-25 · superseded
Inspected
6 of 6 checks · 100%
Scored
2026-09-03 · rubric 1.0.0

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

6 checks3 clean3 flagged
  • Injection surface

    pass25% of grade

    Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

    Scanned 26 text field(s); no instruction-injection patterns found. PASS = no static red flag. A server can serve different tool descriptions at runtime (the rug-pull class), which static scanning cannot see.

  • Supply chain

    fail25% of grade

    Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

    Python build script executes at build time: network call in build script

  • Credential hygiene

    pass15% of grade

    How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

    No hardcoded secrets, secret-shaped tool parameters, or leaked keys found. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

  • Permission scope

    pass15% of grade

    Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

    Network egress present (pyproject declares an HTTP client dependency) — expected for most servers and not a finding on its own. No shell-exec, unbounded/sensitive filesystem, or download-and-run primitives found in scanned source. PASS = no static red flag. Static scanning is blind to code fetched or executed at runtime.

  • Version behavior

    fail10% of grade

    Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

    vs prior 0.25.2 (minor bump): new hardcoded outbound host/BCC destination(s): agentsim.dev, api.agentsim.dev, docs.agentsim.dev, github.com.

  • Transport config

    fail10% of grade

    Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

    remote MCP endpoint declares NO authentication (unauthenticated remote — nginx-ui/CVE-2026-33032 class)

Version history

Each release plotted by grade against the safe line at B. A version that sinks below the line has lost its trusted standing — the shape of a rug-pull.

VersionPublishedGradeScoreInspectedChange
v0.26.1 · current2026-09-02 D556/6 · 100%C→D in v0.26.1
v0.25.22026-09-02 C656/6 · 100%±0
v0.24.22026-08-31 C656/6 · 100%±0
v0.24.12026-08-30 C656/6 · 100%±0
v0.24.02026-08-29 C656/6 · 100%±0
v0.23.12026-08-27 C606/6 · 100%±0
v0.22.12026-08-25 C656/6 · 100%±0
v0.22.02026-08-24 C656/6 · 100%±0
v0.21.02026-06-17 C655/6 · 90%D→C in v0.21.0
v0.20.02026-06-17 D505/6 · 90%C→D in v0.20.0
v0.16.02026-06-10 C655/6 · 90%