openclaw-syncralis
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NODE_ENV | No | Environment mode (e.g., production, development). | production |
| TIMEOUT_MS | No | Timeout in milliseconds for API calls. | 10000 |
| BRAVE_API_KEY | Yes | Your Brave Search API key. | |
| WORKSPACE_DIR | No | Path to workspace directory. Leave empty for auto-detection. | |
| NGROK_API_PORT | No | Port for Ngrok API. | 4040 |
| TAVILY_API_KEY | Yes | Your Tavily API key. | |
| FILE_SERVER_HOST | No | Host for the file server. Use 0.0.0.0 for Docker. | 127.0.0.1 |
| FILE_SERVER_PORT | No | Internal file server port. Use 8451 in Glama (8080 is reserved by mcp-proxy). | 8451 |
| MAX_QUERY_LENGTH | No | Maximum query length in characters. | 2000 |
| PUBLIC_TUNNEL_URL | Yes | Your Ngrok public URL (e.g., https://your-domain.ngrok-free.app). | |
| URL_SIGNING_SECRET | Yes | A 32-character secret for signing URLs. | |
| CONFIRM_TOKEN_TTL_MS | No | Time-to-live for confirmation token in milliseconds. | 300000 |
| MAX_DOWNLOAD_ATTEMPTS | No | Maximum download attempts per link. | 3 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| share_filesA | Reads or shares workspace files. Three actions are available: 'read' — return file contents inline. For PDFs: (1) If the user specifies a page number, read that range directly using pageStart/pageEnd. (2) If searching for a topic, first read pages 1-10 to find the Table of Contents. If no TOC is found in pages 1-10, extend to pages 1-20, then check the final 10 pages as some PDFs place the index at the back. (3) If the PDF has no TOC, scan in 15-page chunks from the beginning until the topic is located. (4) Always read in chunks of 20 pages or fewer. Never request the full PDF in a single call. (5) If a section appears to continue beyond the chunk boundary, read the next chunk to complete it. (6) For PDFs under 15 pages total, reading the entire document in one call is acceptable. 'preview' — REQUIRED first step before sharing. Returns file metadata (name, size, type, modified) and a short-lived confirmationToken. Present ALL metadata to the user and ask for explicit approval before proceeding. Never skip this step. 'download' — generate a public download link. Requires the confirmationToken returned by a prior 'preview' call for the same file. A link CANNOT be generated without a valid token. |
| download_from_urlB | Downloads a file directly from a public or authenticated HTTP/HTTPS URL and saves it to the workspace. |
| web_searchA | Searches the live internet for accurate, up-to-date information. Use for current events. |
| save_shared_fileA | Saves a file provided directly by the AI agent into the workspace. Use this to save generated images, PDFs, DOCX, or text files without needing an external URL download. Binary files MUST be provided as base64 encoded strings. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Most tools are clearly distinct: web_search is isolated, save_shared_file handles AI-provided content, download_from_url handles external URLs, and share_files handles reading and sharing existing files. The only mild overlap is between share_files' 'download' action and download_from_url, but the descriptions clarify the direction of the operation.
All tool names use snake_case and begin with an imperative verb, but the patterns vary slightly: verb+noun (web_search, share_files), verb+adjective+noun (save_shared_file), and verb+preposition+noun (download_from_url). This is mostly consistent and readable, with minor structural deviations.
Four tools form a compact, well-scoped set for the server's apparent purpose: searching the web and managing/sharing workspace files. Each tool has a distinct role, and none feel redundant or excessive.
The core save/read/share loop is covered well: files can be created from agent content or URLs, read inline, previewed, and shared via download links. The main gaps are the absence of explicit listing, deletion, or update operations, which are minor for this narrow file-sharing use case.