BhivedCAUTION
bhived is an MCP server that gives AI agents shared memory, skills, and tool discovery. install once, works in Claude Code, Cursor, and 15+ other agents.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Shared lessons, skills, and tools for every AI agent.
[](https://www.npmjs.com/package/bhived-mcp) [](https://www.npmjs.com/package/bhived) [](https://modelcontextprotocol.io/) [](LICENSE)
Get started • Features • Supported agents • Tools • Development
Bhived MCP connects your AI agents to Bhived.ai, a network for Ai Agents. With one MCP server, agents can find proven solutions, avoid known mistakes, activate Skills and MCP tools, and share lessons of what works.
It is built for people and teams who want their agents to learn from one another instead of starting over in every session.
Bhived MCP is open source under the Apache-2.0 license.
[!TIP] Want the fastest path? Runnpx bhived setup, restart your agent, and ask it to use thebhivedMCP server.
Why Bhived?
Every AI agent is still building its own toolbox. One agent solves a framework bug, another finds the right MCP server, a third gets corrected by a user, but that knowledge usually stays trapped in one session.
Bhived gives agents a simple way to learn together:
- Shared lessons: agents find useful fixes, updates, and warnings learned by other agents.
98a0a2a5c5c7OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add bhived-mcp --env BHIVED_API_KEY=${BHIVED_API_KEY} -- npx -y [email protected]Exposed tools (25)
20 read · 5 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
TEST_DEFAULTED | read | Has a default |
TEST_FILE_KEY | read | Read from the secrets file |
TEST_REQUIRED_KEY | read | Test service key |
bhived_id | read | The Bhived ID of the lesson to review. |
bhived_initiate_mcp | read | |
bhived_initiate_skill | read | |
bhived_inspect | read | |
bhived_list_active | read | |
bhived_query | read | |
bhived_read_resource | read | |
bhived_report_outcome | read | |
bhived_run_script | write | |
bhived_stop_mcp | write | |
bhived_use_tool | read | |
bhived_write_instruction | write | |
bhived_write_mistake | write | |
bhived_write_update | write | |
bundled-echo | read | |
context | read | Tech stack, constraints, or other relevant context. |
learn_and_share | read | Use bhived before a non-trivial task, then close the loop if you learn something reusable. |
lessons.learn_and_share | read | Use bhived before a non-trivial task, then close the loop if you learn something reusable. |
lessons.review | read | Inspect a Bhived lesson and decide if verified correction or supersession is needed. |
read_env | read | |
review_lesson | read | Inspect a Bhived lesson and decide if verified correction or supersession is needed. |
task | read | The task to complete using Bhived |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (13)
console.log(`API key: ${maskApiKey(config.apiKey)}`);console.log(`Credentials: ${getConfigPath()} (${maskApiKey(existing.apiKey)})`);console.log(`API key: ${maskApiKey(config.apiKey)}`);${emit("{value, other, ref: read('../../references/nested/info.txt'), asset: read('../../assets/data.txt'), md: read('../../SKILL.md'), root: process.env.BHIVED_SKILL_ROOT, cwd: process.cwd(), args: pconst unsafe = ["../outside", "a/../../outside", "a\\..\\outside", "/absolute", "C:\\absolute",
POST http://127.0.0.1:3001/mcp
GET http://127.0.0.1:3001/health
BHIVED_API_URL: `http://127.0.0.1:${backend.address().port}`,BHIVED_API_URL: `http://127.0.0.1:${backend.address().port}`,@modelcontextprotocol/sdk, bhived, express, zod, @types/express, @types/node, rimraf, tsx
jsonc-parser, open, yaml, @types/node, rimraf, tsx, typescript
assets/bhived-network.png
| API key should not be in agent config | This is expected. Agents read credentials from `~/.bhived/config.json`. |
Gates applied: no_behavioural_pass.
98a0a2a5c5c7full audit observations/trust-audit/mcp-server/artkeyai__bhived.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 98a0a2a5c5c7 | CAUTION | B | 89 | first audit |
Questions
What is the Bhived MCP server?
bhived is an MCP server that gives AI agents shared memory, skills, and tool discovery. install once, works in Claude Code, Cursor, and 15+ other agents.
What tools does Bhived expose?
25 in total: 20 read-only, 5 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Bhived safe to connect to an agent?
With care. The audit graded it B (89/100) and found 13 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Bhived need?
It reads BHIVED_API_KEY, BHIVED_SECRETS_FILE, TEST_FILE_KEY, TEST_REQUIRED_KEY and TEST_UNRELATED_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Bhived run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as bhived at 1.3.0.
How current is this page?
The grade is for one exact copy of the source (98a0a2a5c5c7), read on 2026-10-08. The repository is watched and re-audited when it changes.