Create a datasource. If type is ambiguous, call search_plugin_information first; install the plugin if needed. IMPORTANT: always call this tool twice. First call: provide only the type — the tool returns a field schema. After receiving the schema, you MUST ask the user for every required field va...
AI agents use create_datasource to create or update resources in Mcp Grafana Npx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Grafana Npx environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | — | Datasource base URL when required by the plugin |
name | string | Yes | Datasource display name |
type | string | Yes | Grafana datasource plugin type, for example prometheus |
access | string | — | How Grafana should access the datasource (proxy or direct) |
fields | object | — | Datasource field values to provision, keyed by field key from the schema returned on the first call. The server uses each field's target (root or jsonData) to p |
database | string | — | Optional database name |
basicAuth | boolean | — | Whether Grafana should use basic auth |
isDefault | boolean | — | Whether this should become the default datasource |
schemaReviewed | boolean | — | Set to true on the second call to confirm you reviewed the schema and collected values from the user. |
withCredentials | boolean | — | Whether Grafana should forward credentials such as cookies |
Parameters from the server's own tool schema.
The tool creates a new datasource in Grafana, which is a reversible configuration change (datasources can be deleted or reconfigured). This falls squarely into the Write category. Severity is high because misconfiguration of datasources—especially with incorrect credentials or malicious connection strings—could expose monitoring systems, leak sensitive data, or redirect metrics to attacker-controlled backends.
From the tool's definition Tool name is 'create_datasource' and description states 'Create a datasource' — this is a data creation operation.
Risk signalsAccepts URL/endpoint input (url) · High parameter count (10 properties) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Create a datasource. If type is ambiguous, call search_plugin_information first; install the plugin if needed. IMPORTANT: always call this tool twice. First call: provide only the type — the tool returns a field schema. After receiving the schema, you MUST ask the user for every required field value explicitly; do not infer or use defaults without user confirmation. Second call: provide the type, the display name in the top-level name argument, schemaReviewed=true, and the fields map populated with values confirmed by the user. Never handle credentials — remind the user to rotate any detected. Returns UID, health check, and a config page link. It is categorised as a Write tool in the Mcp Grafana Npx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
create_datasource accepts 10 parameters: url, name, type, access, fields, database, basicAuth, isDefault, schemaReviewed, withCredentials. Required: name, type. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Grafana Npx MCP server in PolicyLayer and add a rule for create_datasource: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Grafana Npx. Nothing to install.
create_datasource is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_datasource rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for create_datasource. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
create_datasource is provided by the Mcp Grafana Npx MCP server (mcp-grafana-npx). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →