PromptLayer
PromptLayer is the prompt management platform for AI teams. Version prompts, run LLM evals, and monitor agents in production with tracing, logs, and regression sets.
https://www.promptlayer.com/Connect straight to this server’s public endpoint.
https://mcp.promptlayer.com/mcpWe add this server to your workspace, walk through sign-in once, then open Studio with tools ready to run.
Last probed Sep 14, 2026 · mcp.promptlayer.com
84tools discovered
Showing 25 of 84 from the live probe.
Get Prompt Template
Retrieve a fully rendered prompt ready to send to an LLM. Fills in input_variables, resolves snippets, and returns provider-formatted parameters. Use label (e.g. 'prod') or version number to pin a specific version; defaults to latest. WARNING: Snippets are baked into the output — @@@snippet@@@ references are lost. Do NOT use this for editing and re-publishing prompts. Use get-prompt-template-raw instead.
Get Prompt Template Raw
Retrieve prompt template data for inspection or editing. Does not apply input variables. IMPORTANT: Set resolve_snippets=false to preserve @@@snippet_name@@@ references — this is required if you plan to edit and re-publish the prompt, otherwise snippet references will be lost. The response includes a 'snippets' array listing all referenced snippets. Set include_llm_kwargs=true to also get provider-specific parameters.
List Prompt Templates
List all prompt templates in the workspace with pagination. Filter by name, release label, or status.
Publish Prompt Template
Create a new version of a prompt template. Body has two required objects: prompt_template (with prompt_name, tags, folder_id, is_snippet) and prompt_version (with prompt_template content in chat/completion format, commit_message, metadata). Optionally assign release_labels. IMPORTANT: If the prompt uses snippets, preserve @@@snippet_name@@@ markers in the content. Do not inline snippet text — this breaks snippet references. To create a snippet (a reusable fragment referenced by other prompts), s
List Prompt Template Labels
List all release labels assigned to a prompt template.
Create Prompt Label
Attach a release label to a prompt template version. Requires prompt_id (path) and body with prompt_version_number and label name.
Move Prompt Label
Move a release label to a different prompt version. Provide prompt_version_number to reassign the label.
Delete Prompt Label
Delete a release label from a prompt template version.
Get Snippet Usage
Find all prompts that reference a given snippet. Returns prompt names, versions, and labels that use it.
Search Request Logs
Search and filter request logs using structured filters, free-text search, and sorting. Rate limited to 10 req/min, max 25 results/page. FILTER SYNTAX: Use filter_group to combine filters with AND/OR logic. Each filter is {field, operator, value, nested_key?}. Operators by field type: - String fields (engine, provider_type): is, is_not, in, not_in - Text fields (input_text, output_text): contains, not_contains, starts_with, ends_with - Numeric fields (cost, latency_ms, input_tokens, outpu
Get Request
Retrieve a single request's full payload by ID, returned as a prompt blueprint. Includes the prompt template content, model configuration, provider, token counts, cost, timing data, and trace_id (if the request was part of a trace). Useful for debugging, replaying requests, or extracting data for evaluations.
Get Trace
Retrieve all spans for a given trace ID. Each span includes metadata and, if it generated a request log, the associated request_log_id. Useful for inspecting execution flow across multiple LLM calls in a traced operation.
Get Request Search Suggestions
Get autocomplete suggestions for request log search fields. Returns possible values for a given field, optionally filtered by a prefix string. Useful for building search UIs or discovering available values (e.g. which engines, tags, or metadata keys exist in your logs). FIELDS: engine, provider_type, prompt_id, prompt, tags, metadata_keys, status, tool_names, output_keys, input_variable_keys, metadata_values, output_values, input_variable_values. For metadata_values/output_values/input_variabl
Log Request
Log an LLM request/response pair to PromptLayer. Input and output must be in Prompt Blueprint format: {type:'chat', messages:[{role, content:[{type:'text', text}]}]}. Supports structured outputs, tool calls, extended thinking, and error tracking.
Create Spans Bulk
Create OpenTelemetry-compatible spans in bulk for distributed tracing. Each span can optionally include a log_request.
List Smart Tables
List Smart Tables with cursor pagination. Smart Tables are PromptLayer's general-purpose data and computation layer — use them to organise test datasets, run prompt templates across rows, assert on outputs, compare results, build evaluations, or track regression over time. Filter by folder, title, or referenced prompt.
Create Smart Table
Create a Smart Table. By default creates an empty Sheet 1 with one text column (create_default_sheet=true). Set create_default_sheet=false to skip that sheet when you will immediately create your own (create-smart-table-sheet with blank/file/request_logs). Tables are general-purpose — they can hold any tabular data and run computed columns (PROMPT_TEMPLATE, LLM_ASSERTION, CODE_EXECUTION, COMPARE, etc.) over rows. Common uses include evaluations, regression testing, prompt comparisons, and datase
Get Smart Table
Get a Smart Table by UUID, including sheet counts and row counts.
Update Smart Table
Update a Smart Table title or folder.
Delete Smart Table
Delete a Smart Table by UUID. WARNING: This is destructive and cannot be undone. The table is removed from normal Smart Table listings.
List Smart Table Sheets
List sheets in a Smart Table with cursor pagination.
Create Smart Table Sheet
Add a sheet (tab) to a Smart Table. - Omit source to create a blank sheet with a default Column A scaffold, then add columns and rows incrementally. - file: seed rows from a base64-encoded CSV or JSON file (only .csv and .json are supported). Provide title to name the sheet; if omitted, the title falls back to the file name stem. All-empty data rows (every cell empty, including blank lines) are skipped so CSVs stay dense; to create N blank row shells afterward, call add-smart-table-rows with
Get Smart Table Sheet
Get a single Smart Table sheet.
Update Smart Table Sheet
Update a Smart Table sheet title or index.
Delete Smart Table Sheet
Delete a sheet from a Smart Table. WARNING: This is destructive and cannot be undone. Use delete-smart-table to delete the whole table.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Directory coverage for brandsPromptLayer is the prompt management platform for AI teams. Version prompts, run LLM evals, and monitor agents in production with tracing, logs, and regression sets.
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate PromptLayer? Verify ownership to take over this directory entry.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles probed 84 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
PromptLayer may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
MCPBundles is an independent platform built on the open Model Context Protocol standard. Not affiliated with Anthropic PBC or Claude.