MCP server · trust report

io.github.Pseudogiant-xr/pseudolife-mcp

1 check that ran failed — version behavior — so this release can’t be trusted as-is.

Publisher
io.github.Pseudogiant-xr
Repository
github.com/Pseudogiant-xr/Pseudolife-MCP
Install
pypi:pseudolife-mcp, pypi:pseudolife-mcp, pypi:pseudolife-mcp, pypi:pseudolife-mcp, pypi:pseudolife-mcp, pypi:pseudolife-mcp, pypi:pseudolife-mcp, pypi:pseudolife-mcp, pypi:pseudolife-mcp
Versions
9
Inspected
5 of 6 checks · 75%
Scored
2026-09-04 · 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 checks1 clean4 flagged1 not inspected
  • Injection surface

    unscannable25% of grade

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

    No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.

  • Supply chain

    pass25% of grade

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

    Python build script has no build-time network/exec; repository linkage verified

  • Credential hygiene

    warn15% of grade

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

    tests/test_release_ux.py: contains a hardcoded Slack token (xoxb…en (len 21)) — in an example/sample file; verify it is not a real key. Reads secrets from the environment (e.g. pseudolife_memory/briefing_cli.py) — the recommended intake shape.

  • Permission scope

    warn15% of grade

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

    has both shell/exec and network egress — capable of download-and-run, though no such path was observed (pseudolife_memory/backup_cli.py: subprocess.* call; pseudolife_memory/briefing_cli.py: outbound HTTP/socket call). discloses shell/exec capability: pseudolife_memory/backup_cli.py: subprocess.* call discloses shell/exec capability: pseudolife_memory/shim.py: subprocess.* call Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.

  • 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 0.14.0 (minor bump): new capability primitive(s) in source: dynamic-eval, fs-write, http-client, net, subprocess; new hardcoded outbound host/BCC destination(s): 127.0.0.1, anthropic.com, bench.invalid, cf, cfg, cp, docs.anthropic.com, download.pytorch.org, env, evil.example, example.com, example.test, f, getzep.com, github.com, host.docker.internal, p, pseudolife-extractor, pseudolife-migrate-embeddings-test.invalid, raw.githubusercontent.com, rohitraj.tech, unused, www.w3.org, x, x.test.

  • Transport config

    warn10% of grade

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

    manifest/source references telemetry behavior — disclosure

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
v0.15.0 · current2026-09-03 C705/6 · 75%B→C in v0.15.0
v0.14.02026-08-20 B1004/6 · 65%±0
v0.13.02026-08-08 B1003/6 · 55%±0
v0.12.02026-08-01 B87.55/6 · 75%±0
v0.11.02026-07-29 B77.55/6 · 75%±0
v0.10.02026-07-20 B87.55/6 · 75%±0
v0.9.02026-07-19 B77.55/6 · 75%±0
v0.8.12026-07-16 B1003/6 · 55%