TEAA
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
TEAA
TEAA (ToolsEnabled Agent Architecture) provides Fleet, ToolsEngine, and Knowledge through one local MCP connection.
Alpha status: TEAA 0.5.0-alpha.6 is an alpha release. Interfaces and behavior may change between releases.
Install the free launch release
The release assets are published on the TEAA GitHub releases:
Linux x64:
teaa-0.5.0-alpha.6-linux-x64.tar.gzNative Windows x64:
teaa-0.5.0-alpha.6-windows-x64.zipChecksums:
SHA256SUMS
Linux
Download the Linux archive and SHA256SUMS into one directory, then run:
sha256sum -c --ignore-missing SHA256SUMS
tar -xzf teaa-0.5.0-alpha.6-linux-x64.tar.gz
cd teaa-0.5.0-alpha.6-linux-x64
./install.shNative Windows
Download the Windows zip and SHA256SUMS. In PowerShell, run Get-FileHash .\teaa-0.5.0-alpha.6-windows-x64.zip -Algorithm SHA256 and compare the result with the Windows zip line in SHA256SUMS. Extract the zip, open Command Prompt in the extracted teaa-0.5.0-alpha.6-windows-x64 folder, and run:
install.cmdNode.js 22.19 or newer and Python 3.11 or newer are required on both systems. Git is required for Knowledge repository operations. Python does not have to be on PATH: set knowledge.command and knowledge.args in the TEAA settings as SETUP.md describes. After installation, create or choose an absolute project folder and run:
teaa setup --folder <absolute-project-folder> --actor local --no-browser --workers
teaa doctor
teaa config --server-jsonRegister the JSON from teaa config --server-json as a stdio MCP server in your client. See TEAA SETUP.md for first-run details.
Related MCP server: D-Hub MCP Server
Source installation
This repository holds the TEAA 0.5.0-alpha.6 source, but it is not an installable tree. Install from the release archives above. The installers (install.sh, scripts/install.cmd) install a packaged release: they verify the archive's release-manifest.json, and the archive also carries the staged runtimes listed in its vendor/manifest.json (Fleet, ToolsEngine with its Node.js dependencies, and Knowledge). This checkout contains the component sources but not those files, so ./install.sh run here stops with an error about release-manifest.json.
To run the tests from a checkout, use Node.js 22.19 or newer, Python 3.11 or newer and Git, and run npm test. Tests that run setup with the bundled runtime need the staged runtimes from a release archive and fail in a bare checkout.
See SETUP.md for configuration and first-run details.
Report a problem or get help
Something broken or confusing: open an issue and pick Report a problem. Include the version that
teaa doctorshows and the steps to reproduce. Never paste passwords, tokens, API keys or private keys.An idea: open an issue and pick Suggest an improvement.
Your toolsenabled.ai account or the hosted service: email support@toolsenabled.ai.
A security problem: report it privately as the security policy describes, never in a public issue.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
- aXDeprecatedio.github.ax-platform
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides browser automation, audio transcription, and LLM chat as MCP tools for any agent.7MIT
- AlicenseNot gradedqualityBmaintenanceProvides a unified multi-agent coordination layer with shared memory, wiki, skills, and file management via MCP tools, enabling agents to access and collaborate on resources in a single Python process.MIT
- AlicenseNot gradedqualityCmaintenanceServes as a single local MCP entry point that proxies configured upstream MCP tools to multiple coding agents, keeps sessions warm, serializes exclusive services, and provides SQLite-backed task, lock, and memory tools.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to connect once to a local MCP endpoint and access tools from all configured MCP servers, add or remove connectors live, and generate sandboxed connectors for services that lack one. It centralizes multi-server access while keeping credentials isolated and calls logged without recording arguments or results.MIT