Watchlist tracking
Reviewed for relevance and future tracking value.
MCP100 Assessment
Watchlist / Tracking
Why we’re tracking it
Track index quality and tool-contract changes as repository-scale code search evolves
Reviewed · Documentation review; complete setup workflow not independently tested
Best fit
Semantic search across local or remote code repositories for coding agents.
What we know
Semble provides agent-oriented semantic search over local or remote repositories and is designed to run CPU-only without external AI APIs.
Maintenance / activity evidence
- Observed (UTC)fix: Exit the MCP server immediately on stdin EOF or SIGTERM ( 282)
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.
- Reads indexed repository content.
- Authentication not yet verified.
- Sensitive access: Local or cloned repository content
- The main risk is exposing repository content to the connected agent; the project states that indexing does not require external services.
Full authority, access and evidence limits are available in Review context and Access & risk.
Popularity
6,182 repository stars · 97k package downloads / 30 days
Stars observed Oct 6, 2026. Downloads observed Oct 6, 2026.
All limitations / Review context
Does the MCP search surface still expose the documented indexing and retrieval behavior?
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 main risk is exposing repository content to the connected agent; the project states that indexing does not require external services.
- Reads indexed repository content.
- The project states CPU-only operation with no external services or API keys.
- Sensitive access: Local or cloned repository content
- Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
- A project-specific SECURITY.md policy was not available at the fetched official path; the review remains limited to published repository notices.
- No installation, runtime, client matrix, or complete tool-contract audit was performed in this review.
- The fetched official SECURITY.md path returned HTTP 404; it was not treated as positive evidence.
- Index quality depends on repository content and local resources.
Original activity observations
- 2026-10-05T08:34:29Z: fix: Exit the MCP server immediately on stdin EOF or SIGTERM ( 282)
Technical identity
github.com/minishlab/semble- Exact implementation source
- https://github.com/minishlab/semble ↗
- Reviewed resource type
- MCP Server
- Repository identity
- MinishLab/semble
- Package identity
- pypi:semble
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 ↗
minishlab/semble
Recorded repository material and project history.
Includes references whose attribution is not established.
- Evidence source ↗
pypi.org/project/semble/
Source material retained for this review.
Includes references whose attribution is not established.
Setup · Watchlist
Install & Agents
agent-installer
Publisher instructions with a documented client setup path.
Source evidence observed .
Additional setup details required — see the specific gaps below.
Install / connect
Publisher instructionsPublisher: `uv tool install semble` then `semble install` to choose MCP, sub-agent and/or CLI integration in detected coding clients.
package install · Publisher instructions
uv tool install sembleclient registration · Publisher instructions
semble installConfigure / authenticate
Publisher instructionsInstall uv tool install semble then interactive semble install; locally runs CPU keyless; optional MCP and sub-agent integration. Official semble uninstall removes setup.
Check connection
Suggested checkRun `semble --help` and verify the selected MCP integration is discoverable in the chosen client; CLI-only install does not imply MCP connection.
Remove / uninstall / revoke
MCP100 setup guidePublisher-supported integration removal; optional binary removal `uv tool uninstall semble`.
Distinguish client registration removal from software uninstall, persistent data deletion and provider OAuth/API-key revocation.
Remove client registration · MCP100 composed guide
semble uninstall
What it does
Semble provides agent-oriented semantic search over local or remote repositories and is designed to run CPU-only without external AI APIs.
- Capability
- Files & Knowledge
- Resource type
- MCP Server
- Industry
- Software & Technology
- Best fit
- Semantic search across local or remote code repositories for coding agents.
Representative uses
- Search code with natural language
- Find related code and configuration
- Search repository documentation
- Give coding agents repository context
Limitations
- Index quality depends on repository content and local resources.
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
- Reads indexed repository content.
- Data handling
- The project states CPU-only operation with no external services or API keys.
- Cost
- free
- Risk and cautions
- The main risk is exposing repository content to the connected agent; the project states that indexing does not require external services.
Access scope and cautions
- Write actions
- None in the reviewed inventory
- Sensitive access
- Local or cloned repository content
- Risk level
- low
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?
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?
MinishLab is listed as First-party MCP in MCP100’s current evidence.