Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTKEY_API_KEYYesYour Portkey API key

Tools

Functions exposed to the LLM to take actions

NameDescription
list_all_users

List all users in your Portkey organization, including their roles and account details

invite_user

Invite a new user to your Portkey organization with specific workspace access and API key permissions

get_user_stats

Retrieve detailed analytics data about user activity within a specified time range, including request counts and costs

get_user

Retrieve detailed information about a specific user by their ID

update_user

Update a user's profile information including name and organization role

delete_user

Remove a user from your Portkey organization. This action cannot be undone.

list_user_invites

List all pending and sent user invitations in your Portkey organization

get_user_invite

Retrieve details about a specific user invitation

delete_user_invite

Cancel and delete a pending user invitation

resend_user_invite

Resend an invitation email to a pending user

list_workspaces

Retrieve all workspaces in your Portkey organization, including their configurations and metadata

get_workspace

Retrieve detailed information about a specific workspace, including its configuration, metadata, and user access details

create_workspace

Create a new workspace in your Portkey organization

update_workspace

Update an existing workspace's settings and metadata

delete_workspace

Delete a workspace from your organization. This action cannot be undone.

add_workspace_member

Add a user to a workspace with a specific role

list_workspace_members

List all members of a workspace with their roles

get_workspace_member

Get details about a specific member of a workspace

update_workspace_member

Update a member's role in a workspace

remove_workspace_member

Remove a user from a workspace

list_configs

Retrieve all configurations in your Portkey organization, including their status and workspace associations

get_config

Retrieve detailed information about a specific configuration, including cache settings, retry policies, and routing strategy

create_config

Create a new configuration with cache, retry, and routing settings

update_config

Update an existing configuration's cache, retry, or routing settings

delete_config

Delete a configuration by slug. This action cannot be undone.

list_config_versions

List all versions of a configuration to view its change history

list_virtual_keys

Retrieve all virtual keys in your Portkey organization, including their usage limits, rate limits, and status

create_virtual_key

Create a new virtual key for a provider (e.g., openai, anthropic). Virtual keys securely store provider API keys.

get_virtual_key

Retrieve detailed information about a specific virtual key by its slug

update_virtual_key

Update an existing virtual key's name, API key, note, or limits

delete_virtual_key

Delete a virtual key by slug. This action cannot be undone.

create_api_key

Create a new Portkey API key for authentication. Organisation-level keys provide full access, workspace keys are scoped.

list_api_keys

List all API keys in your Portkey organization with optional pagination and workspace filtering

get_api_key

Retrieve detailed information about a specific API key by its UUID

update_api_key

Update an existing API key's name, description, scopes, or limits

delete_api_key

Delete an API key by UUID. This action cannot be undone.

list_collections

List all prompt collections in your Portkey organization. Collections group prompts by app (e.g., hourlink, apizone, research-pilot).

create_collection

Create a new prompt collection for organizing prompts by app. Use one collection per app (hourlink, apizone, research-pilot).

get_collection

Retrieve detailed information about a specific collection

update_collection

Update a collection's name or description

delete_collection

Delete a collection by ID. This action cannot be undone. Prompts in this collection will become orphaned.

create_prompt

Create a new prompt template in Portkey. Prompts are versioned message templates with variable substitution support.

list_prompts

List all prompts in your Portkey organization with optional filtering by collection, workspace, or search query

get_prompt

Retrieve detailed information about a specific prompt including its template, parameters, and version history

update_prompt

Update an existing prompt template. Creates a new version with the changes.

delete_prompt

Delete a prompt by its ID. This action cannot be undone and will remove the prompt and all its versions.

publish_prompt

Publish a specific version of a prompt, making it the default version that will be used when the prompt is called. This is useful for promoting a tested version to production.

list_prompt_versions

List all versions of a specific prompt with their details, including version number, description, template content, and creation date.

render_prompt

Render a prompt template by substituting variables, returning the final messages without executing

run_prompt_completion

Execute a prompt template with variables and get the model completion response. REQUIRES billing metadata (client_id, app, env).

migrate_prompt

Create or update a prompt based on whether it exists. Useful for CI/CD and prompt-as-code workflows. Finds existing prompts by name within the collection.

promote_prompt

Promote a prompt from one environment to another (e.g., staging → prod). Copies the current version to the target environment.

validate_completion_metadata

Validate billing metadata before running a completion. Checks for required fields (client_id, app, env) and valid values.

get_cost_analytics

Retrieve detailed cost analytics data over time, including total costs and averages per request

get_request_analytics

Retrieve request analytics as time-series data, showing total, successful, and failed requests over time

get_token_analytics

Retrieve token usage analytics as time-series data, showing total, prompt, and completion tokens over time

get_latency_analytics

Retrieve latency analytics as time-series data, showing average, p50, p90, and p99 latency percentiles over time

get_error_analytics

Retrieve error count analytics as time-series data, showing total error counts over time

get_error_rate_analytics

Retrieve error rate analytics as time-series data, showing the percentage of failed requests over time

get_cache_hit_latency

Retrieve cache hit latency analytics as time-series data, showing total and average latency for cache hits over time

get_cache_hit_rate

Retrieve cache hit rate analytics as time-series data, showing hit rate percentage, total hits, and misses over time

get_users_analytics

Retrieve user activity analytics over time, showing active and new user counts

list_guardrails

List all guardrails in your Portkey organization with optional filtering by workspace or organization

get_guardrail

Retrieve detailed information about a specific guardrail, including its checks and actions configuration

create_guardrail

Create a new guardrail with specified checks and actions for content moderation and security

update_guardrail

Update an existing guardrail's name, checks, or actions configuration

delete_guardrail

Delete a guardrail by its ID or slug. This action cannot be undone.

list_usage_limits

Retrieve all usage limits in your Portkey organization. Usage limits control how much of a resource (tokens, requests, cost) can be consumed within a time period.

get_usage_limit

Retrieve detailed information about a specific usage limit by its ID

create_usage_limit

Create a new usage limit to control resource consumption within a time period

update_usage_limit

Update an existing usage limit's configuration

delete_usage_limit

Delete a usage limit by ID. This action cannot be undone.

list_rate_limits

Retrieve all rate limits in your Portkey organization. Rate limits control how many requests can be made within a time window.

get_rate_limit

Retrieve detailed information about a specific rate limit by its ID

create_rate_limit

Create a new rate limit to control request frequency within a time window

update_rate_limit

Update an existing rate limit's configuration

delete_rate_limit

Delete a rate limit by ID. This action cannot be undone.

list_audit_logs

Retrieve audit logs for your Portkey organization. Audit logs track all administrative actions including user management, configuration changes, and access events. Supports filtering by time range, actor, action type, and resource.

create_prompt_label

Create a new prompt label to categorize and organize prompts. Labels can be color-coded and scoped to workspaces or organizations.

list_prompt_labels

List all prompt labels in your Portkey organization with optional filtering by workspace, organisation, or search query

get_prompt_label

Retrieve detailed information about a specific prompt label

update_prompt_label

Update an existing prompt label's name, description, or color

delete_prompt_label

Delete a prompt label by ID. This action cannot be undone.

create_prompt_partial

Create a new prompt partial (reusable text snippet) that can be included in prompts using mustache syntax like {{> partial_name}}

list_prompt_partials

List all prompt partials in your Portkey organization with optional filtering by collection

get_prompt_partial

Retrieve detailed information about a specific prompt partial including its content and version info

update_prompt_partial

Update an existing prompt partial. Creates a new version with the changes.

delete_prompt_partial

Delete a prompt partial by ID. This action cannot be undone.

list_partial_versions

List all versions of a prompt partial to view its change history

publish_partial

Publish a specific version of a prompt partial, making it the default version

create_feedback

Create feedback for a specific trace/request. Use this to capture user feedback (thumbs up/down, ratings) on AI generations. Feedback is linked via trace_id and can include custom metadata for analysis.

update_feedback

Update existing feedback by ID. Allows modifying the feedback value, weight, or metadata after initial creation.

list_traces

List all traces in your Portkey workspace with optional filtering. Returns trace metadata including requests, responses, costs, and token usage.

get_trace

Retrieve detailed information about a specific trace by ID. Returns full request/response data, all spans, metadata, cost, token usage, and any associated feedback.

insert_log

Insert a log entry (or multiple entries) into Portkey for tracking AI requests and responses

create_log_export

Create a new log export job to export logs matching specified filters

list_log_exports

List all log export jobs for a workspace

get_log_export

Get details of a specific log export by its ID

start_log_export

Start a log export job that was previously created

cancel_log_export

Cancel a running log export job

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/s-b-e-n-s-o-n/portkey-admin-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server