Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Bee by HEOSSI

PYPI · BEE-SDK · SCANNED SEP 20

Bee by HEOSSI: governed multimodal intelligence - chat, code, security, research, documents, memory.

Available components

0 this week 86 Trust /100
Trust breakdown (7 categories)

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 → Why this is hard to 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 & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • 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 44 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability85
  • 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 1317 tokens (~73/item across 18 items; 14 tools + 4 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage94
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 83% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Bee by HEOSSI MCP server?

Bee by HEOSSI runs locally as a PyPI package, launched with uvx bee-sdk. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · bee-sdk

# add to Claude Code
claude mcp add heossihq-bee-public -- uvx bee-sdk
// .cursor/mcp.json
{
  "mcpServers": {
    "heossihq-bee-public": {
      "command": "uvx",
      "args": [
        "bee-sdk"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "heossihq-bee-public": {
      "command": "uvx",
      "args": [
        "bee-sdk"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add heossihq-bee-public -- uvx bee-sdk
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "heossihq-bee-public": {
      "type": "local",
      "command": [
        "uvx",
        "bee-sdk"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add heossihq-bee-public --command uvx --arg bee-sdk
# ~/.hermes/config.yaml
mcp_servers:
  heossihq-bee-public:
    command: "uvx"
    args: ["bee-sdk"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "heossihq-bee-public": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "bee-sdk"
      ]
    }
  }
}
# add to Vellum
assistant mcp add heossihq-bee-public -t stdio -c uvx -a bee-sdk
// mcp.json
{
  "mcpServers": {
    "heossihq-bee-public": {
      "command": "uvx",
      "args": [
        "bee-sdk"
      ]
    }
  }
}
Changelog

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.

  • 20 Sept 26 0
    • Stability: 0.97 → pass security
  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 13 Sept 26 0
    • Stability: 0.97 → pass security
  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 +1
    • Schema quality: excellent → good functional
  • 7 Sept 26 −3
    • Stability: pass → 0.80 functional
Diagnostics

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 20 Sept 2026 · Analysed pypi/bee-sdk@0.6.10

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 14 exposed · ~1,228 tokens

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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
bee_chat ~124

Use for general or specialist questions that do not require a more specific Bee tool. Returns generated text from the selected domain and model tier. The gateway enforces the API key's plan, tenant policy, token allowance, and usage metering.

NameTypeReqDescription
domainstringOptional domain specialist (defaults to general).
max_tokensintegerMax response tokens
messagestringyesThe question or request
modelstringOptional Bee model tier. Limited to your plan. Default: bee-cell.
temperaturenumberSampling temperature (optional)

No output schema declared.

No examples provided.

bee_code ~130

Use for code explanation, bug fixing, refactoring, or test generation. Returns text and proposed code; it does not read files, execute commands, or modify a repository. Choose the intended operation with action.

NameTypeReqDescription
actionstringyesWhat to do with the code
codestringyesThe code
errorstringError message / bug description (for action=fix)
focusstringWhat to optimise for (for action=refactor)
frameworkstringTest framework (for action=write_tests)
languagestringProgramming language

No output schema declared.

No examples provided.

bee_documents_add ~77

Use only when the user intends to persist supplied text in the authenticated tenant's hosted Bee knowledge base. Creates a searchable document and consumes the plan's document allowance; it does not read local files by itself.

NameTypeReqDescription
contentstringyesThe document text to ingest
sourcestringA name / source label for the document

No output schema declared.

No examples provided.

bee_documents_search ~66

Use to retrieve relevant excerpts from the authenticated tenant's hosted Bee document library. Returns ranked chunks and source labels without changing the library; requires a RAG-entitled plan.

NameTypeReqDescription
kintegerHow many chunks to return
querystringyesWhat to search for

No output schema declared.

No examples provided.

bee_memory_add ~76

Use only when the user intends Bee to persist a fact for future conversations. Writes to the authenticated user's memory, honors opt-in and tenant policy, and automatically suppresses near-duplicates.

NameTypeReqDescription
contentstringyesThe fact to remember (≤ 4000 chars)
kindstringWhat kind of memory this is

No output schema declared.

No examples provided.

bee_memory_search ~66

Use to recall facts, preferences, projects, or skills from the authenticated user's Bee memory. Returns ranked memories without changing them and honors the user's memory setting and tenant policy.

NameTypeReqDescription
querystringyesWhat to recall
top_kintegerHow many memories to return

No output schema declared.

No examples provided.

bee_quantum_reasoning_get ~57

Use to inspect one tenant-scoped Lab job. Returns status, candidates, scores, result, QPU or fallback evidence, usage, and receipt ID without changing the job.

NameTypeReqDescription
job_idstringyesJob UUID

No output schema declared.

No examples provided.

bee_quantum_reasoning_jobs ~73

Use to list the authenticated tenant's retained Quantum Reasoning Lab jobs and capabilities. Returns paginated metadata without creating or changing jobs.

NameTypeReqDescription
cursorstringOpaque cursor from the previous page
limitinteger
modelstring
statusstring

No output schema declared.

No examples provided.

bee_quantum_reasoning_remove ~51

Use only after explicit user intent to cancel an eligible queued job or permanently erase content from a terminal job. This is a destructive, tenant-scoped operation.

NameTypeReqDescription
job_idstringyes

No output schema declared.

No examples provided.

bee_quantum_reasoning_run ~98

Use only after the user chooses an eligible hosted quantum product. Creates a durable, tenant-encrypted, metered Quantum Reasoning Lab job that may incur simulator or QPU cost. Returns a job record; inspect it with bee_quantum_reasoning_get.

NameTypeReqDescription
modelstringyes
productstringyes
promptstringyesThe problem and decision criteria
provider_connection_idstring

No output schema declared.

No examples provided.

bee_research ~116

Use to draft a NISQ-honest quantum-circuit design or critique an ML/CS paper. Returns research text or sample framework code; it does not submit QPU work. Use bee_quantum_reasoning_run for a durable hosted Lab job.

NameTypeReqDescription
focusstringCritique focus (for paper_critique)
frameworkstringQuantum framework (for quantum_design)
inputstringyesThe task to design, or the abstract to critique
taskstringyesResearch task

No output schema declared.

No examples provided.

bee_security ~138

Use for defensive code audits, threat models, authorized penetration-test support, or smart-contract review. Returns analysis and remediation guidance only; it does not scan a target or execute exploits and refuses unauthorized weaponization.

NameTypeReqDescription
contextstringAuthorised-engagement scope (for task=pentest_assist)
frameworkstringFramework (for task=threat_model): STRIDE, PASTA, LINDDUN
inputstringyesCode, system description, contract source, or finding
languagestringLanguage (for code_audit / smart_contract_review)
taskstringyesSecurity task

No output schema declared.

No examples provided.

bee_usage ~83

Use to inspect the authenticated caller's Bee plan and metered consumption. Returns pooled tokens, per-tier allowances, reset times, and a 24-hour or 7-day breakdown. It never changes billing, credits, or entitlements.

NameTypeReqDescription
windowstringBreakdown window: 'day' (24h) or 'week' (7d). Default 'day'.

No output schema declared.

No examples provided.

bee_verify_provenance ~73

Use to verify a Bee agentic coding session by session_id. Returns verification status, sealed-turn count, and ML-DSA-65 (NIST FIPS 204) signature details; it does not alter or replay the session.

NameTypeReqDescription
session_idstringyesThe agent session id to verify

No output schema declared.

No examples provided.

Common questions

What is the Bee by HEOSSI MCP server?

Bee by HEOSSI is an MCP server listed in the public MCP registry as io.github.heossihq/bee-public. Bee by HEOSSI: governed multimodal intelligence - chat, code, security, research, documents, memory. This page covers its PyPI package (bee-sdk).

Is the Bee by HEOSSI MCP server safe to use?

Bee by HEOSSI scores 86 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Bee by HEOSSI MCP server expose?

Bee by HEOSSI exposes 14 tools: bee_chat, bee_code, bee_security, bee_research, bee_verify_provenance, and 9 more. Their descriptions and schemas cost roughly 1,228 tokens of context every time the server is loaded.

Is the Bee by HEOSSI MCP server still maintained?

Bee by HEOSSI is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Bee by HEOSSI MCP server under?

Bee by HEOSSI declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.