Bee — The Progressive Intelligence Engine
PYPI · BEE-SDK · SCANNED AUG 3
Bee — The Progressive Intelligence Engine: tiered LLM, 4 tools, hosted API, free tier.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency19
- Repository check failed: the declared repository URL redirects; it must resolve directly. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 3 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability81
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 827 tokens (~68/item across 12 items; 8 tools + 4 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
- Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.
pypi · bee-sdk
claude mcp add cuilabs-bee -- uvx bee-sdk
codex mcp add cuilabs-bee -- uvx bee-sdk
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"cuilabs-bee": {
"type": "local",
"command": [
"uvx",
"bee-sdk"
],
"enabled": true
}
}
} openclaw mcp add cuilabs-bee --command uvx --arg bee-sdk
mcp_servers:
cuilabs-bee:
command: "uvx"
args: ["bee-sdk"] {
"mcpServers": {
"cuilabs-bee": {
"command": "uvx",
"args": [
"bee-sdk"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 3 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Aug 26 +18
- Malware scan: unverified → pass ▲ security
- Stability: unverified → 0.23 ▲ functional
- 31 Jul 26 −8
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 30 Jul 26 −18
- Malware scan: pass → unverified ▼ security
- 27 Jul 26 +8
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Jul 26 68
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 3 Aug 2026 · Analysed pypi/[email protected]
Provenance none
Ecosystem: pypi · Outcome: none
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Dependencies 0 packages
0 packages in the resolved dependency tree.
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.
bee_chat Ask Bee ~132
Ask Bee anything. Bee — The Progressive Intelligence Engine — is a tiered LLM platform with per-domain specialisation. Optionally pick a domain and a model tier; both are limited to what your API key's plan allows. Bee is honest about uncertainty rather than fabricating.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | — | Optional domain specialist (defaults to general). |
| max_tokens | integer | — | Max response tokens |
| message | string | yes | The question or request |
| model | string | — | Optional Bee model tier. Limited to your plan. Default: bee-cell. |
| temperature | number | — | Sampling temperature (optional) |
No output schema declared.
No examples provided.
bee_code Code Assistant ~115
Programming help from Bee's code specialist: explain code, fix a bug, refactor, or write tests — pick via `action`.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | What to do with the code |
| code | string | yes | The code |
| error | string | — | Error message / bug description (for action=fix) |
| focus | string | — | What to optimise for (for action=refactor) |
| framework | string | — | Test framework (for action=write_tests) |
| language | string | — | Programming language |
No output schema declared.
No examples provided.
bee_documents_add Add Document ~69
Add a document to your Bee knowledge base so bee_documents_search (and Bee) can use it. Scoped to your account; counts against your plan's document limit.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | The document text to ingest |
| source | string | — | A name / source label for the document |
No output schema declared.
No examples provided.
bee_documents_search Search Documents ~62
Search your Bee documents (RAG) — returns the top matching chunks with their source. Scoped to your account; requires a rag-entitled plan.
| Name | Type | Req | Description |
|---|---|---|---|
| k | integer | — | How many chunks to return |
| query | string | yes | What to search for |
No output schema declared.
No examples provided.
bee_memory_add Remember ~70
Save a fact to your Bee personal memory so Bee recalls it in future conversations. Scoped to your account; near-duplicates are de-duplicated automatically.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | The fact to remember (≤ 4000 chars) |
| kind | string | — | What kind of memory this is |
No output schema declared.
No examples provided.
bee_memory_search Search Memory ~56
Search your Bee personal memory — facts, preferences, projects and skills Bee has remembered about you. Scoped to your account.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | What to recall |
| top_k | integer | — | How many memories to return |
No output schema declared.
No examples provided.
bee_research Research Assistant ~98
Bee's research specialist: design a quantum circuit (NISQ-honest, Qiskit) or critique an ML/CS paper — pick via `task`.
| Name | Type | Req | Description |
|---|---|---|---|
| focus | string | — | Critique focus (for paper_critique) |
| framework | string | — | Quantum framework (for quantum_design) |
| input | string | yes | The task to design, or the abstract to critique |
| task | string | yes | Research task |
No output schema declared.
No examples provided.
bee_security Security Assistant ~136
Bee's security specialist: audit code, build a threat model, assist authorised penetration testing, or review a smart contract — pick via `task`. Refuses weaponisation / unauthorised targets.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | — | Authorised-engagement scope (for task=pentest_assist) |
| framework | string | — | Framework (for task=threat_model): STRIDE, PASTA, LINDDUN |
| input | string | yes | Code, system description, contract source, or finding |
| language | string | — | Language (for code_audit / smart_contract_review) |
| task | string | yes | Security task |
No output schema declared.
No examples provided.