BaseThread MCPThe public home for
ai.basethread/basethread
None
Overview
From the repository's own README, as read at the audited commit.
# BaseThread MCPThe public home for [BaseThread](https://basethread.ai)'s Model Context Protocol server , its registrymanifest, install guide, and security page.BaseThread is one shared context your whole team's AI tools read and write over MCP. Claude Code, Cursor,ChatGPT, Windsurf, and Copilot each read the relevant slice of a shared, company-structured context graphat the start of a session and write activity, decisions, and tasks back as work happens , so no onere-explains the project and answers stop contradicting. Free to start, no card.## ConnectThe server is hosted (remote, streamable-HTTP + OAuth) , no local install needed:```bashclaude mcp add --transport http basethread https://mcp.basethread.ai/mcp```Or add `https://mcp.basethread.ai/mcp` in any MCP client that supports remote servers. Full instructionsfor every client, plus the tool list: **[llms-install.md](./llms-install.md)**.## In this repo- **[server.json](./server.json)** , the Official MCP Registry manifest (`ai.basethread/basethread`).- **[llms-install.md](./llms-install.md)** , agent-readable install + configuration guide.- **[Security & privacy](https://basethread.ai/security)** , the canonical security page (access model, OAuth, tenancy). Mirrored in [SECURITY.md](./SECURITY.md).- **[PUBLISHING.md](./PUBLISHING.md)** , how the registry listing is published and republished.## Links- Product: https://basethread.ai- App: https://app.basethread.ai- Live demo (no signup): https://app.basethread.ai/demo- MCP endpoint: https://mcp.basethread.ai/mcp
Details
- Source
- navbuildz/basethread-mcp
- Transports
- streamable-http
- Tools
- Registered at runtime; the list could not be read from source.
- Stars
- 0 · pushed 66d ago
Trust audit
Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (4)
streamable-http
sudo mv mcp-publisher /usr/local/bin/
Gates applied: no_behavioural_pass, no_license.
Audited 2026-09-13 · audit v0.4.0 · source sha eae38149c561 · full audit: observations/trust-audit/mcp-server/navbuildz__basethread.json · Report an issue or request a re-scan
Audit history
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-13 | eae38149c561 | SAFE | B | 85 | source changed, verdict held |
Also audited
Servers with a similar trust profile.
Questions
What is the ai.basethread/basethread MCP server?
None
Is ai.basethread/basethread safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (85/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does ai.basethread/basethread need?
No credential environment variables were found in its source, so it appears to need none.
How does ai.basethread/basethread run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (eae38149c561), read on 2026-09-13. The repository is watched and re-audited when it changes.
Provenance: OBSERVED · read 2026-09-13 · job trust-audit-2026-09-13