Watchlist tracking
Reviewed for relevance and future tracking value.
MCP100 Assessment
Watchlist / Tracking
Why we’re tracking it
Track agent and MCP client compatibility as the fast-moving personal-agent surface changes
Reviewed · Documentation review; complete setup workflow not independently tested
Best fit
Self-hosted personal AI agent runtime with tools, memory, MCP integrations and scheduled automation.
What we know
nanobot is a self-hosted personal AI agent runtime that combines tools, memory, MCP integrations, model routing, multi-agent delegation, scheduled automation and an OpenAI-compatible API.
Maintenance / activity evidence
- Observed (UTC)fix(mcp): let streamable HTTP read timeout cover tool timeout
Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.
Verification gaps / watch-outs
- Installation and comprehensive security have not been independently audited.
- Depends on enabled tools and connected providers. Writes: Depends on enabled tools.
- Authentication not yet verified.
- Sensitive access: Potential access to configured tools, files or provider credentials
- The runtime can inherit the authority of configured tools and provider credentials; review each connector's scope.
Full authority, access and evidence limits are available in Review context and Access & risk.
Popularity
48,826 repository stars · 47k package downloads / 30 days
Stars observed Oct 6, 2026. Downloads observed Oct 6, 2026.
All limitations / Review context
Does nanobot still expose the documented MCP transport and tool behavior across supported clients?
The bounded assessment reviewed the official README, repository notices, security policy path, and security page for known material public-tracking blockers. No such blocker was identified. This is a public-tracking assessment, not an installation safety certification.
- The runtime can inherit the authority of configured tools and provider credentials; review each connector's scope.
- Depends on enabled tools and connected providers.
- Self-hosted runtime; connected tools/providers may receive task data.
- Reviewed write actions: Depends on enabled tools
- Sensitive access: Potential access to configured tools, files or provider credentials
- Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
- No independent runtime, installation, or comprehensive security audit was performed.
- No installation, runtime, client matrix, or complete tool-contract audit was performed in this review.
- Exact per-tool permission boundary
- Authentication, permissions and data flow depend on the connected providers and tools.
Original activity observations
- 2026-10-05T17:41:10Z: fix(mcp): let streamable HTTP read timeout cover tool timeout
Technical identity
github.com/hkuds/nanobot- Exact implementation source
- https://github.com/hkuds/nanobot ↗
- Reviewed resource type
- Framework
- Repository identity
- HKUDS/nanobot
- Package identity
- pypi:nanobot-ai
Evidence & Sources
- Evidence basis
- Recorded source evidence
- Setup runtime verification
- Not independently runtime-tested by MCP100 for this setup workflow.
Reviewed · Latest source observation
- GitHub repository ↗
hkuds/nanobot
Recorded repository material and project history.
Includes references whose attribution is not established.
- Evidence source ↗
pypi.org/project/nanobot-ai/
Source material retained for this review.
Includes references whose attribution is not established.
Setup · Watchlist
Framework setup
Publisher instructions.
Source evidence observed .
Additional setup details required — see the specific gaps below.
Install / connect
Publisher instructionsPublisher-specific setup path. Follow prerequisites, then register or connect to your MCP host.
publisher documented install or connect · Publisher instructions · Review before use
python -m pip install nanobot-ai nanobot onboard --wizardConfigure / authenticate
Publisher instructionsnanobot is an MCP CLIENT/HOST, not an installable standalone MCP server. Add external servers under `tools.mcpServers` in ~/.nanobot/config.json.
Check connection
Suggested checkRun `nanobot agent -m "Hello!"`, then confirm an intentionally configured MCP tool is available.
Remove / uninstall / revoke
MCP100 setup guideRemove the third-party entry from `tools.mcpServers` to disconnect an MCP. To retire the host itself, uninstall nanobot separately; preserve config/data.
What it does
nanobot is a self-hosted personal AI agent runtime that combines tools, memory, MCP integrations, model routing, multi-agent delegation, scheduled automation and an OpenAI-compatible API.
- Capability
- AI & Reasoning
- Resource type
- Framework
- Best fit
- Self-hosted personal AI agent runtime with tools, memory, MCP integrations and scheduled automation.
Representative uses
- Run local terminal or web agents
- Connect MCP and web tools
- Delegate work across agents
- Schedule recurring automations
Limitations
- Authentication, permissions and data flow depend on the connected providers and tools.
Reviewed access
Access & risk
Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.
- Authentication
- Not documented in the reviewed sources
- Permissions
- Depends on enabled tools and connected providers.
- Data handling
- Self-hosted runtime; connected tools/providers may receive task data.
- Cost
- free
- Risk and cautions
- The runtime can inherit the authority of configured tools and provider credentials; review each connector's scope.
Access scope and cautions
- Write actions
- Depends on enabled tools
- Sensitive access
- Potential access to configured tools, files or provider credentials
- Risk level
- moderate
FAQ
Based on reviewed evidence as of 2026-10-06. Watchlist tracking is not a recommendation or a security certification.
Which tasks are documented for this implementation?
What setup information is documented?
Can it modify data or perform write operations?
What data-handling boundary should I consider?
What limitations and risks should I check before use?
Is this an official MCP?
HKUDS is listed as Community implementation in MCP100’s current evidence.