Schema | sealchat-agent-mcp

sealchat-agent-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`SEALCHAT_AGENT_TOKEN`	No	The API token for the SealChat Agent API (usually starts with 'agt_'). Required unless using a config file or inline agent URLs.
`SEALCHAT_AGENT_CONFIG`	No	Path to a JSON config file containing baseUrl and token. Environment variables take precedence.
`SEALCHAT_AGENT_PROFILE`	No	Profile name; defaults to 'default'.	default
`SEALCHAT_AGENT_BASE_URL`	No	The base URL of the SealChat deployment (e.g. https://your-sealchat.example/). Required unless using a config file or inline agent URLs.
`SEALCHAT_AGENT_MAX_PAGES`	No	Maximum number of pages to fetch during pagination; defaults to 10000.	10000
`SEALCHAT_AGENT_STATE_FILE`	No	Path to a state file for checkpointing incremental sync.
`SEALCHAT_AGENT_TIMEOUT_MS`	No	Timeout in milliseconds for HTTP requests; defaults to 10000.	10000
`SEALCHAT_AGENT_MAX_RETRIES`	No	Maximum number of retries for retriable HTTP errors; defaults to 3.	3
`SEALCHAT_AGENT_MAX_BACKOFF_MS`	No	Maximum backoff in milliseconds between retries; defaults to 30000.	30000
`SEALCHAT_AGENT_ALLOW_INLINE_URL`	No	Set to '1' to allow passing agent_url as a tool argument. When enabled, base URL and token may be omitted if agent_url is provided per call. Defaults to '0'.	0

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivitySlowing

ResponsivenessNo issues