Integration

YepCode integration

YepCode is a serverless platform that runs JavaScript and Python processes in the cloud. Run a process synchronously or asynchronously with JSON parameters, follow executions and their logs, rerun or kill them, create, edit, version and alias processes and reusable script library modules, schedule processes by cron or date, manage team variables, the team's npm and pip dependencies and files in the team storage bucket. Not exposed: interactive sandboxes (driven over gRPC), raw file upload and the token exchange route; team variable values, process webhook passwords and process public access tokens are left out of every output. Authentication is OAuth 2.0 client credentials: create an API credential in YepCode Settings, API Credentials, and enter its Client ID and Client Secret plus your team id (the slug in cloud.yepcode.io/<team>).

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in YepCode.Built from the 56 YepCode tools below, on the connection you add once.

What you can do with YepCode

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Alias, 10 operations

  • create_module_version_aliasCreate module version aliasPOSTCreates a named alias that points at one published version of a script library module.
  • create_process_version_aliasCreate process version aliasPOSTCreates a named alias (for example production) that points at one published version of a process, so callers can run the alias instead of a fixed tag.
  • delete_module_version_aliasDelete module version aliasDELETEDeletes a module version alias.
  • delete_process_version_aliasDelete process version aliasDELETEDeletes a process version alias. Callers that run the process by this alias stop finding it.
  • get_module_version_aliasGet module version aliasGETReturns one version alias of a script library module and the version it points at.
  • get_process_version_aliasGet process version aliasGETReturns one version alias of a process and the version it points at.
  • list_module_version_aliasesList module version aliasesGETLists the version aliases of a script library module, optionally only those pointing at versionId. Paginated, page is 0-based.
  • list_process_version_aliasesList process version aliasesGETLists the version aliases of a process (named pointers such as production that resolve to one version), optionally only those pointing at versionId. Paginated, page is 0-based.
  • update_module_version_aliasUpdate module version aliasPATCHRenames a module version alias or points it at another published version (versionId). Leave a field out to keep its current value.
  • update_process_version_aliasUpdate process version aliasPATCHRenames a process version alias or points it at another published version (versionId). Leave a field out to keep its current value.

Version, 8 operations

  • delete_module_versionDelete module versionDELETEDeletes one published version of a script library module.
  • delete_process_versionDelete process versionDELETEDeletes one published version of a process. Schedules or callers that run that version by tag stop finding it.
  • get_module_versionGet module versionGETReturns one published version of a script library module, including its tag and source code.
  • get_process_versionGet process versionGETReturns one published version of a process, including its tag, source code, readme and parameters schema.
  • list_module_versionsList module versionsGETLists the published versions of a script library module, paginated (page is 0-based, limit per page).
  • list_process_versionsList process versionsGETLists the published versions of a process, paginated (page is 0-based, limit per page). Each version carries its tag, source code and parameters schema.
  • publish_module_versionPublish module versionPOSTPublishes a new immutable version of a script library module from the given source code, with a tag (for example 1.0.0) and a comment. Processes can import a module by version.
  • publish_process_versionPublish process versionPOSTPublishes a new immutable version of a process from the given source code, with a tag (for example 1.0.0), readme, comment and parameters schema. A version can then be run by tag or aliased.

Process, 7 operations

  • create_processCreate processPOSTCreates a new process with source code, configuration, and metadata. The process can be written in JavaScript or Python and includes parameter schemas for form generation.
  • delete_processDelete processDELETEPermanently deletes a process and all its associated data including executions and schedules. This action cannot be undone.
  • execute_process_asyncExecute process asyncPOSTStarts a process run in the background and returns its executionId at once. Read status and returnValue with get_execution, and output with list_execution_logs.
  • execute_process_syncExecute process syncPOSTRuns a process and waits for it to finish, returning the value the process code returns (any JSON). The execution id is sent in the Yep-Execution-ID response header; use execute_process_async for long runs.
  • get_processGet processGETRetrieves detailed information about a specific process including its configuration, source code, and metadata.
  • list_processesList processesGETRetrieves a paginated list of processes with optional filtering by keywords and tags. Processes are executable code units that can be scheduled or triggered manually.
  • update_processUpdate processPATCHUpdates an existing process with new configuration, source code, or metadata. All fields provided will replace the existing values.

Schedule, 7 operations

  • delete_scheduleDelete scheduleDELETEPermanently deletes a scheduled process and cancels all future executions. This action cannot be undone.
  • get_scheduleGet scheduleGETRetrieves detailed information about a specific scheduled process including its configuration, schedule settings, and current status.
  • list_schedulesList schedulesGETLists scheduled processes (cron or one-time runs), paginated (page is 0-based), optionally filtered by processId or by keywords matching the process name or schedule comment.
  • pause_schedulePause schedulePUTPauses a currently active scheduled process. The process will stop executing until it is resumed.
  • resume_scheduleResume schedulePUTResumes a previously paused scheduled process. The process will continue executing according to its original schedule configuration.
  • schedule_processSchedule processPOSTSchedules a process: give cron (a standard five-field cron expression) for recurring runs, or dateTime for a single run, plus the input to pass on each run. Returns the created schedule.
  • update_scheduleUpdate schedulePATCHUpdates an existing scheduled process with new configuration, schedule settings, or parameters. All provided fields will replace the existing values.

Module, 5 operations

  • create_moduleCreate modulePOSTCreates a new script library module with source code and metadata. Modules can be written in JavaScript or Python and can be imported by processes.
  • delete_moduleDelete moduleDELETEPermanently deletes a script library module. This action cannot be undone and may affect processes that import this module.
  • get_moduleGet moduleGETRetrieves detailed information about a specific script library module including its source code, metadata, and version information.
  • list_modulesList modulesGETRetrieves a paginated list of script library modules. Modules are reusable code libraries that can be imported and used across different processes.
  • update_moduleUpdate modulePATCHUpdates an existing script library module with new source code or metadata. All provided fields will replace the existing values.

Dependency, 4 operations

  • discard_team_dependencies_installDiscard team dependencies installDELETEDiscards the staged dependency changes for the specified programming language, reverting to the last installed state.
  • get_team_dependenciesGet team dependenciesGETRetrieves the current dependency manifest for the specified programming language, including installed dependencies and any pending installation.
  • install_team_dependenciesInstall team dependenciesPOSTTriggers the installation of staged dependencies for the specified programming language. The manifest must have a pending installation before calling this endpoint.
  • update_team_dependenciesUpdate team dependenciesPUTReplaces the team's whole dependency list for one language and stages it; call install_team_dependencies to install. Read get_team_dependencies first and send the full list back with your change.

Execution, 4 operations

  • get_executionGet executionGETRetrieves detailed information about a specific execution including its status, parameters, results, and metadata.
  • kill_executionKill executionPUTTerminates a running execution immediately. This operation sends a kill signal to stop the execution process and marks it as killed.
  • list_executionsList executionsGETRetrieves a paginated list of process executions with optional filtering by keywords, process, status, and date range. Executions represent individual runs of processes.
  • rerun_executionRerun executionPOSTCreates a new execution using the same parameters and configuration as the specified execution. This is useful for reproducing or retrying failed executions.

Variable, 4 operations

  • create_variableCreate variablePOSTCreates a new team variable that can be used across processes and executions. Variables can be marked as sensitive to hide their values in logs and UI.
  • delete_variableDelete variableDELETEPermanently deletes a team variable. This action cannot be undone and may affect processes that depend on this variable.
  • list_variablesList variablesGETLists the team variables (keys usable from every process), paginated (page is 0-based, limit per page). Values are not returned by this tool.
  • update_variableUpdate variablePATCHUpdates an existing team variable with new value or configuration. Sensitive variables will have their values hidden in logs and UI.

Storage object, 3 operations

  • delete_storage_objectDelete storage objectDELETEPermanently deletes a file from the team's storage bucket. This action cannot be undone.
  • download_storage_objectDownload storage objectGETDownloads one file of the team storage bucket and returns it as a stored file. filename is the object name as listed by list_storage_objects (it may contain slashes).
  • list_storage_objectsList storage objectsGETRetrieves a list of storage objects in the team's storage bucket. Objects can be filtered by prefix to organize files in folders.

Team, 2 operations

  • get_teamGet teamGETRetrieves the current team's information including parent team slugs.
  • update_teamUpdate teamPATCHPartially updates the current team. Only provided fields are updated. For parentTeamSlugs: omit to keep unchanged, pass an empty list to clear all parents.

Log, 1 operation

  • list_execution_logsList execution logsGETRetrieves the log entries for a specific execution, providing detailed information about the execution process and any output or errors.

Signed url, 1 operation

  • create_storage_signed_urlCreate storage signed urlPOSTCreates a time-limited signed URL to download an existing object of the team storage bucket directly, without this API. It expires after expiresInSeconds (default 3600, maximum 604800 = 7 days).

Use YepCode from Claude Code, Cursor or Codex

Connect YepCode in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its YepCode operations become tools the client can call, next to every other integration you connected.

Claude Code
claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"
Codex (~/.codex/config.toml)
[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"
Cursor, Claude Desktop and other JSON configs
{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect YepCode

  1. Create your workspace

    Sign up free. Nothing to install.

  2. Connect YepCode once

    Add your YepCode connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.

  3. Describe the job in chat

    The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

YepCode integration FAQ

What can you do with the YepCode integration?

LiveContext exposes 56 operations on YepCode, covering alias, version, process and schedule.

Popular integrations

Browse the whole catalog