Tally Prime MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP server port | 3000 |
| PASSWORD | No | OAuth authentication password (required for remote deployments) | |
| BIND_HOST | No | Bind address (0.0.0.0 only behind reverse proxy) | 127.0.0.1 |
| MCP_DOMAIN | No | Public-facing URL | http://localhost:3000 |
| TALLY_HOST | No | Tally Prime XML server hostname | localhost |
| TALLY_PORT | No | Tally Prime XML server port | 9000 |
| ADMIN_SECRET | No | Optional secret for manual client registration | |
| CLAUDE_MODEL | No | Anthropic model for GUI agent | claude-sonnet-4-20250514 |
| CORS_ORIGINS | No | Comma-separated allowed origins | MCP_DOMAIN |
| OPENAI_MODEL | No | OpenAI model for GUI agent | gpt-4o |
| READONLY_MODE | No | Set true to disable all write tools | false |
| TALLY_EDITION | No | Tally edition: silver or gold | silver |
| LLM_MAX_TOKENS | No | Max tokens per LLM response | 300 |
| OPENAI_API_KEY | No | OpenAI API key for LLM-guided GUI agent (optional) | |
| TALLY_EXE_PATH | No | Tally executable path | C:\Program Files\TallyPrime\tally.exe |
| TALLY_INI_PATH | No | Path to tally.ini | C:\Program Files\TallyPrimeEditLog\tally.ini |
| LLM_TIMEOUT_SEC | No | LLM API request timeout in seconds | 30 |
| TALLY_DATA_PATH | No | Tally data directory | C:\Users\Public\TallyPrime\data |
| TALLY_DEBUG_XML | No | Set to '1' to enable tally-raw-xml-probe tool | |
| LOG_RETAIN_COUNT | No | Max rotated log files to keep | 10 |
| ANTHROPIC_API_KEY | No | Anthropic API key for LLM-guided GUI agent (optional) | |
| AUTH_CODE_EXPIRY_MS | No | Authorization code TTL in ms | 600000 |
| AUTH_RATE_LIMIT_MAX | No | Max auth attempts per window | 10 |
| ANTHROPIC_API_VERSION | No | Anthropic API version header | 2023-06-01 |
| DB_TABLE_RETENTION_MS | No | DuckDB temp table TTL in ms | 900000 |
| TALLY_COMPANIES_CONFIG | No | Optional credential-hint config path for list-available-companies | <TALLY_DATA_PATH>/.tally-mcp-companies.json |
| ACCESS_TOKEN_EXPIRY_SEC | No | Access token TTL in seconds | 3600 |
| AUTH_RATE_LIMIT_WINDOW_MS | No | Rate limit window in ms | 60000 |
| TOKEN_CLEANUP_INTERVAL_MS | No | Expired token cleanup interval in ms | 60000 |
| OPEN_COMPANY_GUI_MAX_STEPS | No | Max LLM-guided steps per command | 25 |
| OPEN_COMPANY_GUI_TIMEOUT_SEC | No | GUI agent timeout in seconds | 180 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessResponsive