endly-mcp
Retrieve and use Endly MCP skills and tools in Codex for service orchestration, complete e2e suites, selected cases, task discovery, and stateful debugging.
Skill by viant
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/viant-endly-mcp
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/endly-mcp
What's inside
- Skill name
endly-mcp- Description
- Retrieve and use Endly MCP skills and tools in Codex for service orchestration, complete e2e suites, selected cases, task discovery, and stateful debugging.
- License
- Apache-2.0
- Instructions
- 46 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- body: contains an absolute path from the author's machine
Files (1)
- SKILL.md
SKILL.md (first lines)
Discover tools belonging to the connected Endly MCP server. Use `endly_skill_list` and follow its nextCursor pages; retrieve `endly-orchestration`, `endly-authoring`, `endly-testing`, `endly-mcp-debug`, and the applicable service or project skill via `endly_skill_get` with its returned URI. Read references from the returned resource inventory using `endly_resource_read`. Native clients can use skills/list, skills/get and resources/read. Retrieve only the guidance needed for the current operation. For project requests, retrieve the explicitly configured project skill and relevant dsunit function skills. Preserve the original Endly loader's instance -> workflow/default -> workflow resource fallback. Do not require a test.yaml per instance when a valid default exists. Check actual lookup candidates when all fallback resources are missing. Open a session, load the root workflow, list its tasks and template instances, select paths/IDs in user-requested order, then run through MCP. Inspect operation status/events/output and state paths. Debug, step, resume and rerun through the same session rather than replacing the orchestration with shell commands. Loading only prepares the definitions; operations execute actions. Skill content is guidance, not a grant of execution authorization. Check the requested test environment. If the connection is unavailable, explain the missing connection and provide this setup using a built executable from the Endly checkout: ```sh cd /Users/awitas/go/src/github.com/viant/endly go build -o /absolute/path/endly-mcp ./endly codex mcp add endly -- /absolute/path/endly-mcp mcp codex mcp list ``` For workflows using WorkingDirectory, configure the server cwd to the e2e directory, or launch with a script that cd's there and execs the built binary with `mcp`. The default stdio mode keeps stdout reserved for MCP messages. For an existing HTTP process use `endly mcp -transport=streamable -addr=127.0.0.1:4981` and connect to its `/mcp` endpoint. Use a fresh Codex session after changing server configuration. Do not edit user MCP configuration unless requested. Setup command reference: https://developers.openai.com/codex/mcp . Local server behavior is documented in `server/mcp/README.md` in the Endly checkout. Prefer endly_listInstances(filter, offset, limit) over full task dumps. Poll concise endly_getOperation, then request only relevant event pages or state paths. A zero-assertion or skipped run is not an e2e success. For stalled Go operations retrieve endly-go-diagnostics and enable -diagnostics for gops stacks. Native source service tools are available for dsunit, HTTP runner/endpoints and validators. They accept sessionId, request and optional timeoutMillis; request schemas come from registered Endly routes. Poll the returned operation, filter/page its events, and inspect targeted state paths.
From viant/endly, Apache-2.0.
More from viant/endly
- 0.760score
endly-dbunit
viant
Author and diagnose Endly SQL fixture preparation, validation, query and schema workflows using the dbunit service; preserve dsunit for legacy and NoSQL…
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-dsunit-hydration
viant
Hydrate Endly use-case fixtures over preloaded dictionaries, with database mappings, sequence-backed IDs, and published per-case state.
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-http-followup
viant
Chain Endly HTTP requests by delegating IDs, headers, URLs, and payloads from one response into subsequent calls and validations.
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-go-diagnostics
viant
Diagnose stalled Endly Go orchestration with gops stacks, operation events, and targeted state inspection before fixing the underlying code.
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-http-mocks
viant
Orchestrate Endly HTTP mock servers and recorded conversations with deterministic matching, per-case responses, and cleanup.
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-orchestration
viant
Orchestrate Endly services and nested workflows with ordered tasks, shared state, setup and cleanup, conditions, and asynchronous operation control through MCP.
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-authoring
viant
Author, inspect, and run Endly YAML workflows, including task selectors, nested tasks, state, UDFs, and database fixtures.
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-dsunit-batch-validation
viant
Validate Endly batches by use-case IDs across database expectations, asynchronous logs, and aggregate outputs with bounded waits.
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-testing
viant
Design and diagnose Endly integration and e2e tests with isolated fixtures, sequence-backed IDs, API and database assertions, and focused reruns.
SkillAFreshness: A★ 269Claude Code +9 - 0.752score
endly-mcp-debug
viant
Discover, run, rerun, pause, step, resume, and diagnose Endly workflows and e2e instances through stateful MCP tools.
SkillAFreshness: A★ 269Claude Code +9 - 0.752score
endly-gcp-run
viant
Author and run Endly gcp/run service actions and diagnose their requests, responses, and workflow integration.
SkillAFreshness: A★ 269Claude Code +9 - 0.752score
endly-workflow
viant
Author and run Endly workflow service actions and diagnose their requests, responses, and workflow integration.
SkillAFreshness: A★ 269Claude Code +9
Signals
- Stars
- 269
- Forks
- 39
- Open issues
- 0
- Last commit (this folder)
- Sep 30, 2026 (27 days ago)
- Last release
- Oct 21, 2026 (6 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/viant/endly
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from viant
- 0.760score
endly-dbunit
viant
Author and diagnose Endly SQL fixture preparation, validation, query and schema workflows using the dbunit service; preserve dsunit for legacy and NoSQL…
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-authoring
viant
Author, inspect, and run Endly YAML workflows, including task selectors, nested tasks, state, UDFs, and database fixtures.
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-testing
viant
Design and diagnose Endly integration and e2e tests with isolated fixtures, sequence-backed IDs, API and database assertions, and focused reruns.
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-dsunit-batch-validation
viant
Validate Endly batches by use-case IDs across database expectations, asynchronous logs, and aggregate outputs with bounded waits.
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-dsunit-hydration
viant
Hydrate Endly use-case fixtures over preloaded dictionaries, with database mappings, sequence-backed IDs, and published per-case state.
SkillAFreshness: A★ 269Claude Code +9 - 0.755score
endly-go-diagnostics
viant
Diagnose stalled Endly Go orchestration with gops stacks, operation events, and targeted state inspection before fixing the underlying code.
SkillAFreshness: A★ 269Claude Code +9
Cite this page
endly-mcp skill. Agent Mart. https://agentmart.dev/skills/viant-endly-mcp (last updated 2026-10-24)