Causly Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | Fine-grained GitHub token with contents, issues and pull requests permissions | |
| GROQ_API_KEY | No | Groq API key used for meeting transcription | |
| VERCEL_TOKEN | No | Vercel API token (project must be Git-linked for deploys) | |
| LINEAR_API_KEY | No | Linear personal API key | |
| NOTION_API_KEY | No | Notion API key; share each page or database with the integration | |
| CAUSLY_TIMEZONE | No | Optional IANA timezone name, e.g. Asia/Kolkata; defaults to your machine's zone | |
| GMAIL_CLIENT_ID | No | Google OAuth Desktop app client ID for Gmail | |
| SLACK_BOT_TOKEN | No | Slack bot token (search:read needs a user token) | |
| TELEGRAM_CHAT_ID | No | Telegram chat ID to receive reminders and alerts | |
| SENTRY_AUTH_TOKEN | No | Sentry auth token; add event:write to resolve or comment | |
| SECRETS_MASTER_KEY | No | 32-byte hex key for the local encrypted secrets manager | |
| TELEGRAM_BOT_TOKEN | No | Telegram bot token created with @BotFather | |
| GMAIL_CLIENT_SECRET | No | Google OAuth Desktop app client secret for Gmail | |
| GMAIL_REFRESH_TOKEN | No | Google refresh token for Gmail; generated by `causly-server login google` | |
| SUPABASE_ACCESS_TOKEN | No | Supabase Management API access token | |
| CALENDAR_REFRESH_TOKEN | No | Google refresh token for Google Calendar; uses the same Google client as Gmail |
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 | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_toolsA | Find tools by keyword across ALL toolsets, including ones not loaded yet. Call with no query to list every toolset. |
| load_toolsetA | Load one or more toolsets (e.g. 'git', 'github', 'docker') so their tools become available. Use search_tools to discover toolset names. |
| use_toolA | Call any tool by name, even one that is not in your tool list yet (its toolset loads automatically). Use this when load_toolset says your client may not show new tools. Set describe=true to see a tool's parameters first. |
| read_fileB | Read the full text content of a single file. |
| read_multiple_filesB | Read multiple files in a single call. Failures on individual files do not stop the batch. |
| create_fileA | Create a brand-new file. Fails if the file already exists (use write_file to overwrite). |
| write_fileB | Create or completely overwrite a file with new content. Creates parent directories if needed. |
| edit_fileA | Edit a file via exact string find-and-replace, without rewriting the whole file. old_str must match exactly and be unique unless replace_all is set. |
| delete_fileA | Delete a single file. DESTRUCTIVE — requires confirm: true. |
| move_fileC | Move or rename a file or directory. |
| copy_fileC | Copy a single file to a new location. |
| get_file_infoB | Get metadata about a file or directory: size, type, created/modified timestamps. |
| list_directoryC | List the immediate files and subfolders inside a directory. |
| directory_treeB | Recursively build a tree view of a directory's contents (skips node_modules and .git). |
| create_directoryB | Create a new directory, including any missing parent directories. |
| delete_directoryA | Delete a directory. Recursive by default so it removes nested contents too. DESTRUCTIVE — requires confirm: true. |
| search_filesC | Recursively search for files/folders whose name contains a given pattern (case-insensitive). |
| run_commandA | Run a shell command in a given working directory (npm install, npm run build, pip install, tests, etc.). A short list of catastrophic patterns (drive wipes, format, shutdown) is blocked; everything else executes with full permissions. HIGH risk — requires confirm: true. |
| project_detectA | Detect a project's language, framework, and package manager by inspecting its manifest files. |
| project_infoB | Get structured project info: language, framework, package manager, resolved test/lint/typecheck/build commands, and current git branch/remotes. |
| project_healthB | Get a health snapshot of a project: git cleanliness/ahead-behind, whether dependencies are installed, and which env files are present. |
| run_testsB | Detect and run the project's test command, returning stdout/stderr/exit_code. |
| run_lintC | Detect and run the project's lint command, returning stdout/stderr/exit_code. |
| run_typecheckB | Detect and run the project's typecheck command, returning stdout/stderr/exit_code. |
| run_buildB | Detect and run the project's build command, returning stdout/stderr/exit_code. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| ship-feature | Guide for taking a code change from request to open PR using this server's tools. |
| fix-ci | Guide for diagnosing and fixing a failing GitHub Actions run using this server's tools. |
| deploy-project | Guide for safely deploying and verifying a project using this server's tools. |
| review-changes | Guide for reviewing an open PR's diff, discussion, and CI status using this server's tools. |
| process-meeting | Transcribe a recording or read a transcript, then save notes, action items with reminders, and link the deal. |
| meeting-prep | Brief on the calendar event, pipeline deal, past meetings and open action items before a call. |
| pipeline-review | Look at open deals, stale deals and due follow-ups, and decide what to do next. |
| prospecting | Find companies that need your services, get a public contact, and add the best ones to the pipeline. |
| cofounder | Operating instructions that turn the connected agent into a technical co-founder: how to use these tools, when to ask for approval, and how to stay safe. |
| follow-up-review | Go through reminders that are due, suggest next actions, and close or snooze them. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 25 tools
Most tools have clearly distinct purposes, especially the file CRUD/search operations and the run_* wrappers. A few boundaries are fuzzy: project_detect vs project_info overlap, and run_command overlaps with run_tests/run_lint/run_typecheck/run_build. search_tools, load_toolset, and use_tool are related but distinguishable.
All names use snake_case, giving a predictable surface. However, the pattern is not strictly verb_noun: directory_tree, project_info, project_health, and project_detect are noun-ish phrases while most others follow verb_noun. The deviation is minor and still readable.
Twenty-five tools is at the heavy end for this server, even though it spans filesystem operations, project automation, and dynamic toolsets. Some consolidation is possible, especially project_detect/project_info/project_health and the four run_* wrappers around run_command. The count is borderline rather than clearly wrong.
The filesystem surface covers create, read, write, edit, move, copy, delete, list, tree, search, and metadata, which is strong CRUD coverage. Project automation covers detection, health, test/lint/typecheck/build execution, and arbitrary commands. Minor gaps include directory copy and built-in git operations, though load_toolset can extend coverage.