Camber - Remote Agentic Data Science
Server Details
Remote data science agents for Snowflake, Databricks & BigQuery in Claude/Cursor via MCP
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.3/5 across 6 of 6 tools scored.
Each tool has a distinct purpose: chat start, chat status, agent creation, agent listing, usage guide, and user info. No overlap or ambiguity between them.
Most tools follow a verb_noun snake_case pattern (e.g., agents_chat_start, agents_create). However, usage_guide and user_info deviate slightly as noun_noun, which introduces minor inconsistency.
Six tools is well-scoped for an agent management server, covering essential operations without excess. Each tool serves a clear need.
The tool set covers core workflows: creating and listing agents, starting and checking chats, and retrieving user/usage info. Minor gaps like missing update/delete for agents exist but are not critical.
Available Tools
6 toolsagents_chat_startAInspect
Start a Camber agent chat. This is the tool to use for chatting with an agent.
Agent runs can take minutes — longer than MCP tool timeouts allow (Claude Desktop
cannot extend them). So this tool does NOT wait for the reply: it submits the
message and returns immediately with a `conversation_id` and a clickable `chat_url`.
The agent keeps working on the server after this returns.
**You MUST follow up, the reply is NOT in this tool's result:**
1. After calling this tool you MUST tell the user the work is in progress and share the `chat_url` so they can watch it live.
2. Then immediately call the **`agents_chat_status`** tool with the returned `conversation_id`
to get the agent's reply. That tool checks twice over 30 seconds, if the latest
status is `running`, call it again. MUST NOT end your turn until
`agents_chat_status` returns status `idle` (done) or `failed`.
**One run per conversation:** continuing a `conversation_id` that is still `running`
fails with a "still generating a response" error. Either wait and retry after
`agents_chat_status` reports it finished, or call again with `stop=true` to interrupt
the current run and send the new message.| Name | Required | Description | Default |
|---|---|---|---|
| stop | No | Set true to stop the conversation's currently running response and start this message instead. Only meaningful with conversation_id. Use it when a previous call reported the conversation is still generating a response and the user wants to interrupt it and send a new message. | |
| message | No | The message to send to the agent. | |
| agent_tag | No | Tag of the agent you want to chat with. Start with @ to use the agent's tag.agent_tag = `@owner_name.agent_alias`For example, @camber_user.ai-agent-1 | |
| conversation_id | No | Optional UUID of an existing conversation to continue. Pass the conversation_id from a previous agents_chat_start call to keep context across turns. |
Output Schema
| Name | Required | Description |
|---|---|---|
| status | Yes | |
| message | Yes | |
| chat_url | Yes | |
| conversation_id | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavior: non-blocking, timeout issues, immediate return with conversation_id and chat_url, need to poll status, and error conditions for running conversations. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with sections and bullet points, front-loaded with main purpose. Slightly lengthy due to detailed instructions, but every sentence is informative and necessary for correct usage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (async, polling, error handling), the description covers all aspects: how to start, follow-up steps, error conditions, and stop mechanism. Output schema likely provides conversation_id and chat_url, so description complements it perfectly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all 4 parameters at 100%, but description adds value: explains stop usage, conversation_id for continuity, and agent_tag format with example. All parameters are well contextualized.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool starts a Camber agent chat, emphasizing its async nature. It distinguishes from siblings like agents_chat_status by specifying it submits a message and returns immediately, not waiting for the reply.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit step-by-step instructions: after calling, share the chat URL and call agents_chat_status. Explains when to use stop=true and warns against sending messages while a run is active, with retry logic.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
agents_chat_statusAInspect
Check an async agent chat started with agents_chat_start, and return its reply when done.
This checks the CLI twice over 30 seconds and returns its latest status response.
Status values:
- `running`: still working — call this tool again with the same conversation_id.
- `idle`: finished — `content` holds the agent's reply.
- `failed`: the run errored.
Returns: AgentChatStatus with `status`, `content` (the reply once done), and
`output_stash_files`. The run may reference **output files in Camber Stash**
(`stash://...`). Those live in the cloud until copied locally:
`camber stash cp stash://<user>/<path> ./<local>` (see `camber stash cp --help`),
then confirm with the user where files were saved.| Name | Required | Description | Default |
|---|---|---|---|
| conversation_id | No | The conversation_id returned by agents_chat_start, identifying the run to check. |
Output Schema
| Name | Required | Description |
|---|---|---|
| error | Yes | |
| status | Yes | |
| content | Yes | |
| chat_url | Yes | |
| conversation_id | Yes | |
| output_stash_files | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses the polling behavior (checks CLI twice over 30 seconds), status values and their meanings, and the handling of output stash files. This is comprehensive behavioral transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is somewhat wordy, repeating that it checks the async agent chat and mentions the polling behavior twice. It could be more concise without losing clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists, the description adequately covers return values (status, content, output_stash_files) and explains the stash file handling. The tool is simple with one parameter, and the description provides all necessary context for an agent to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%—the parameter is well-described in the schema. The description adds minimal extra context (linking to agents_chat_start), so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks an async agent chat started by agents_chat_start and returns the reply when done. It distinguishes itself from sibling tools like agents_chat_start (which starts the chat) and others (create, list, etc.).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says to call this after agents_chat_start and to call again if status is 'running'. It provides clear context on when to use, though it doesn't explicitly state when not to use or mention alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
agents_createAInspect
Create a Camber agent.
Creates a personal agent by default. Pass `team_name` to create the agent
for a team you belong to. Returns the created agent, including its `tag`.| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Name of the agent to create. | |
| alias | No | Alias used in the agent tag, for example `my-agent` in `@owner.my-agent`. | |
| team_name | No | Optional team unique name. When omitted, creates a personal agent. | |
| description | No | Optional short description of the agent. | |
| instructions | No | Optional instructions that define the agent behavior. | |
| structured_output | No | Whether the agent should return structured output. |
Output Schema
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| tag | Yes | |
| name | Yes | |
| alias | Yes | |
| status | Yes | |
| content | Yes | |
| owner_id | Yes | |
| created_at | Yes | |
| owner_name | Yes | |
| owner_type | Yes | |
| updated_at | Yes | |
| description | Yes | |
| access_level | Yes | |
| instructions | Yes | |
| parent_agent_id | Yes | |
| structured_output | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It does not disclose behavioral traits like destructive nature, authentication needs, or side effects beyond creation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (two sentences) and front-loaded with purpose; no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of an output schema, the description adequately mentions the return includes a tag. However, could add more about permissions or idempotence.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds context for team_name (default personal, team creation). Other parameters are well described in schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Create a Camber agent' and distinguishes personal vs team agents, differentiating it from sibling tools like agents_chat or agents_list.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use team_name but does not provide explicit guidance on when not to use this tool versus alternatives (e.g., agents_list for listing).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
agents_listAInspect
List Camber agents with optional scope and pagination.
Returns: AgentListInfo object containing:
- data: List of AgentInfo objects
- page: PageInfo object with pagination details (page, size, total, num_page)| Name | Required | Description | Default |
|---|---|---|---|
| page | No | The page number to list agents from (default: 1). | |
| size | No | The number of agents to list per page (default: 20). | |
| scope | No | Scope of agents to list. Use 'community' for community agents, 'system' for system agents, 'team' for a specific team, or leave empty (null) to list your personal agents. | |
| team_name | No | Unique name of the team whose agents you want to list. Required when scope is 'team'. Ignored for other scopes. |
Output Schema
| Name | Required | Description |
|---|---|---|
| data | Yes | |
| page | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the burden of behavioral disclosure. It describes the return structure (AgentListInfo with data and page) but does not mention potential side effects or permissions. Since it is a read-only list operation, the lack of destructive hints is acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded. Two sentences: first states the purpose, second details the return object. It is efficient without unnecessary fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (4 parameters, no required params) and the presence of an output schema, the description adequately covers the tool's behavior. It includes return type details. Sibling tools are clearly different, so no confusion.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds context beyond the schema: it explains the scope values ('community', 'system', 'team', null) and clarifies that team_name is required when scope is 'team'. This adds meaningful usage guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'List Camber agents with optional scope and pagination.' It specifies the verb (list) and resource (agents), and distinguishes from siblings by not mentioning chat or usage guide functionalities.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage through the context of listing agents with scope and pagination, but does not explicitly state when to use this tool versus alternatives like agents_chat. However, the purpose is clear enough for an agent to decide.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
usage_guideAInspect
Instructions for correctly using this MCP server. Call at the start of a session to learn tools, auth, CLI prerequisites, and stash file handling.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes the tool as informational ('learn'), implying no side effects. With no annotations, the description adequately conveys safe read behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose, no redundant words. Efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters, simple intent, and a clear list of output content, the description is fully sufficient for an agent to use this tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters; schema coverage is 100%. Description naturally does not need to add parameter info.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it provides instructions for using the MCP server, listing specific topics (tools, auth, CLI prerequisites, stash file handling). No ambiguity with siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Call at the start of a session', providing clear usage context. Does not list alternatives, but siblings are distinct in purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
user_infoAInspect
Get the authenticated Camber user and team names.
Returns email, username, and teams list.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| Yes | ||
| teams | Yes | |
| username | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes read-only operation and specific return fields. Implies authentication context via 'authenticated Camber user'. No annotations, so description carries burden; it discloses behavioral traits sufficiently.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words. Front-loaded with main purpose, followed by details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 0 parameters and presence of an output schema, description adequately covers purpose and return fields. Could mention error cases, but not essential for this simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters; schema coverage is 100%. Baseline 4 per instructions as description doesn't need to add param info.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Get the authenticated Camber user and team names' with specific verb and resource. Lists return fields (email, username, teams list). Distinct from sibling tools which are for agents and usage guide.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance. However, for a simple get-info tool with 0 parameters and no ambiguous siblings, it's minimally adequate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!