Schema | Agent Workspace MCP Server

Agent Workspace MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`LOG_LEVEL`	No	Python logging level (DEBUG, INFO, etc.).	INFO
`COMMAND_TIMEOUT`	No	Default seconds before run_bash kills a process.	60
`MAX_SEARCH_RESULTS`	No	Maximum results returned by search_workspace.	50
`MAX_READ_SIZE_BYTES`	No	Maximum file size for read_file (1MB).	1048576
`MAX_WRITE_SIZE_BYTES`	No	Maximum file size for write_file (5MB).	5242880

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": true }
`logging`	{}
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`extensions`	{ "io.modelcontextprotocol/ui": {} }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
read_fileA	Read a text file. Text only, max 1MB, returns first 100 lines. Use offset/limit for segments or run_bash('grep/head/tail') for large files.
write_fileA	Create or overwrite a file. Creates parent dirs. For partial edits use search_and_replace. Validates .py/.json/.toml/.yaml syntax before writing.
list_directoryA	List directory contents. Returns [F]/[D] prefixed entries. Excludes .git, .venv, pycache.
search_workspaceA	Find files by glob pattern. Returns up to 50 paths. For content search use run_bash with grep.
run_bashA	Run a shell command in /workspace. Returns [Exit code: N] + merged stdout/stderr, truncated at 50KB. Tools: curl, git, jq, patch, tree, fd, rg, zip, tar and standard coreutils. Supports pipes, redirects, &&, \|\|. Python/packages (uv only — no python/pip): uv run script.py Run scripts (auto-installs deps from imports) uv add/remove Manage project dependencies uv init Scaffold new project with pyproject.toml uvx Run CLI tools without install (e.g. uvx ruff check .)
search_and_replaceA	Primary file editing tool — prefer over patch. Replaces substrings with fuzzy whitespace fallback. Returns unified diff. Validates .py/.json/.toml/.yaml syntax.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/HrRodan/agent-workspace-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server