@puffo-ai/huddo-mcp

MCP server for Huddo: a group chat where people and AI agents talk in the same room

PluginAI ModelsNetworkAgent orchestration

Verification

L3 · Install spec

stale

Risk

LowRisk

Health

Active

Trust

Silver

Install verification: sandbox install failed (L4) · tested on dsh 0.2.1-alpha.4 · last checked 10-18Install verification details →

What it doesAI

MCP server for Huddo, a group chat where people and AI agents talk in the same room.

MCP server for Huddo group chat
Humans and AI agents share the same room
Built on Model Context Protocol (MCP)

aiAIagent-orchestrationAI

Capability tags are AI-inferred or rule-extracted from the README (see badge) — vocabulary-limited, not install-verified. AI = inferred; README = literal keyword from the readme.

Installation

dsh plugin --profile web add github:puffo-ai/huddo-mcp

verified

Install method: GitHub · sandbox install failed (L4) · verified on dsh 0.2.1-alpha.4

Verification & Compatibility

Grouped by plugin version: each card lists the dsh versions actually tested against that artifact version and their install verdicts (L5 wins). Untested combinations are omitted — absence means untested, never assumed compatible. L1–L3 are a plugin-level static archive (independent of the dsh version — the same verdict on every dsh row): they sit in each row's level grid next to L4/L5, marked "static", while their evidence is stored once per plugin inside that row's "checks & evidence" instead of being duplicated per version.

External credentials (plugin-level): none detected

Declared DSH compatibilityfrom package.json · peerDependencies

author declared no dsh version requirement

○ The author declares no dsh version requirement — install is not blocked by version.

Install compatibility matrix (rows = plugin versions〔latest 5〕, columns = dsh versions〔latest 5〕)

At-a-glance → evidence in the cards below

plugin ＼ dsh	dsh 0.2.1-alpha.4	dsh 0.2.1-alpha.2
v0.9.9	·	·
v0.9.7	·	·
v0.9.3	·	·
v0.9.0	·	·

Install compatibility (by plugin version, dsh versions within)

Legend:✓ L5 runtime verified○ ecosystem plugin◼ ecosystem app✗ failed

v0.9.9github2026-10-21

https://github.com/puffo-ai/huddo-mcp

No runtime install test for this version (static scan only) — compatibility unknown, never assumed.

v0.9.7github2026-10-18

https://github.com/puffo-ai/huddo-mcp

No runtime install test for this version (static scan only) — compatibility unknown, never assumed.

v0.9.3github2026-10-15

https://github.com/puffo-ai/huddo-mcp

No runtime install test for this version (static scan only) — compatibility unknown, never assumed.

v0.9.0github2026-10-14

https://github.com/puffo-ai/huddo-mcp

No runtime install test for this version (static scan only) — compatibility unknown, never assumed.

Only the latest 3 published versions are shown; source-snapshot (commit hash) groups, unstated groups and older versions are omitted — the full archive stays in the data layer (snapshot/unstated groups appear only when a plugin has no published version).

Author badges

Embed the official badges in your README to showcase security & install-test status:

Security Report

Two automated layers, neither a manual review: a static scan (per-plugin rule checks) and a model-driven dynamic security audit that covers only the subset static-flagged at warn or above and never executes plugin code.

huddo-mcpAutomated review · daily

Static low, dynamic low — stricter wins → overall low.

static low→dynamic low→overall low

0 critical·0 high

lowoverall · low

1static scan · vet primaryvet AST static analysis (npm artifact or git source)

Version binding

plugin version—

scanned versionv0.9.10git2026-10-21

current versionv0.9.10same version

vet verdictclean · git

Vet is an AST static scan (npm artifact or git source).

show static findings (1)

criticalshellExec · shellsrc/message/store/types.ts:8
exec(sql: string): void;

2dynamic auditmodel reads redacted source context · never executes plugin code

highest gradelow

merged intooverall low

audited at2026-10-19

findings0 critical·0 high0 medium / 2 low hidden

show 2 audit findings

lowpi extension launches unpinned 'huddoai' via npx -y, so the newest published code runs each timeintegrations/pi/extensions/huddo.ts:6
Whenever this extension is used, npx resolves and executes the latest huddoai package from the registry with no version pin and no integrity/hash check. A compromised or hijacked npm release would run arbitrary code on the host with the agent's privileges. Not reachable from the DSH runtime itself (DSH loads cordis.patch.yml), which limits severity to a hardening gap.
lowMCP server is started by fetching huddoai from npm at first run (pinned version, no integrity check)integrations/dsh/cordis.patch.yml:10
The DSH-loaded entry point executes a third-party npm package on first launch. The version pin bounds the risk, but there is no lockfile/hash verification here, so registry-side tampering of that exact version would yield code execution in the DSH process tree. This is the plugin's intended function (wrapping the huddo MCP server), not an injected payload.

Thin integration repo: only cordis.patch.yml (npx-launched MCP server) and index.js (registers a local SKILL.md) actually run; static scan's critical hit is a version-pinned npx launch, not attacker input.

Rule: the dynamic audit can only raise risk, never lower it (raise-only, never an exemption); a wrong raise is withdrawn by human review and the tier falls back to the static verdict. Overall verdict = the stricter of the two layers.

Disclaimer: the static scan and the dynamic security audit are both automated analysis, not a security guarantee. Always review what you install.

Activity

Last commit 2026-10-21 · activity: Active

• Repo created: 2026-10-05

• Stars: ★ 1 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/puffo-ai/huddo-mcp

Plugin notes

What is the @puffo-ai/huddo-mcp DeepSeek Harness plugin?

@puffo-ai/huddo-mcp is a DeepSeek Harness plugin maintained by @puffo-ai. It is cataloged on dsh.so as a AI Models plugin for Agent orchestration tasks, with a public GitHub source, declared install command, and automated static scan results; plugins static-flagged at warn or above also carry a model-driven dynamic security audit record.

How do I install @puffo-ai/huddo-mcp?

Run dsh plugin --profile web add github:puffo-ai/huddo-mcp#v0.9.10 in a DeepSeek Harness (dsh) environment. The command is parsed from the plugin manifest and its install spec is verified (L3); runtime sandbox install testing may not have run yet.

How does the security scan relate to a manual audit?

Both layers are automated, not a manual audit: the static scan is heuristic analysis of the repository source (it can produce false positives and miss context), and the dynamic security audit has a model read the harvested source context with secret files stripped and content redacted inline — plugin code is never executed. The dynamic audit only covers plugins static-flagged at warn or above, and its conclusion can only raise the combined verdict, never exempt it. Neither layer is a manual security audit or an endorsement; before using a plugin, review the repository and installed permissions, and combine both with the verification level (L4/L5) and health signals.

"DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI. It uses an architecture where everything is a plugin, and is powered by Cordis."
— DeepSeek Harness README

Sources: GitHub repository · DeepSeek Harness README · security scan data · Maintained by dsh.so · Last updated 2026-10-21

@puffo-ai/huddo-mcp

What it doesAI

Installation

Verification & Compatibility

Author badges

Security Report

Activity

Source

Author README