Test AI workflow automation with your team. Compare multi-agent workflows, measure quality and cost, and decide where human-in-the-loop review belongs.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 3, 2026 · mcp.skillsimm.com
19tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://mcp.skillsimm.com/mcp
Skill page: https://www.mcpbundles.com/skills/skillsimm-mcp-425c025d74
Explore capabilities (19)
read 1
write 2
other 16
Create
2
Other capabilities
17
Start Template Interview
other
start_template_interview
Start the guided template-creation interview. Returns the interview_id
and the first question — relay each question to your user, then call
answer_interview_question with their answer.
Start Template Interview — Start the guided template-creation interview. Returns the interview_id
and the first question — relay each question to your user, then call
answer_interview_question with their answer.
Answer Interview Question — Record the user's answer to the current interview question. Returns the
next question, or {done: true, summary} when the interview is complete —
then call finish_interview to create the draft.
Finish Interview — Materialize a completed interview as a SkillSimm draft template
(visibility=draft, owned by you). Returns the created template.
Create Template Draft — Create an empty draft template directly (skip the interview). Add steps
with add_step. The draft is private (visibility=draft) until reviewed.
Add Step — Append a step to a draft.
actor_mode: human | human_with_ai | team_with_ai | ai.
task_type: multiple_choice | numeric_input | structured_response | open_response | document_review.
ai_assist (for *_with_ai): suggests | critiques | grades | decides.
grading examples: {"type":"answer_key","options":[...],"correct_answer":"...","points":2}
or {"type":"rubric","criteria":["..."],"points":3} or
{"type":"numeric","expected_value":42,"tolerance":1,"points":1}.
Edit Step — Update fields of an existing step (only the fields you pass change).
Covers actor mode, task description, and grading-rule edits.
Remove Step — Remove a step from a draft (also drops other steps' references to it).
List My Templates — List templates you own (drafts and submitted).
Validate Template — Run the full package validation — the same checks the GitHub Actions
required PR check runs. Fix every error before submitting.
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.
Test AI workflow automation with your team. Compare multi-agent workflows, measure quality and cost, and decide where human-in-the-loop review belongs.
How do I connect SkillSimm to my AI agent?
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.
How many tools does SkillSimm provide?
Operate this server?
Request removal if you do not want SkillSimm listed here, or claim the listing if you want to manage it on MCPBundles.
Operate SkillSimm?
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 publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
Generate Preview — Preview the exact package files a submission PR would contain
(README, template.yaml, steps.yaml, grading.yaml…).
Submit To Github Review — Submit the draft for review: validates the package, then opens a pull
request on the SkillSimm submissions repo. Merge of that PR (after human
review) is what publishes the template — agents cannot publish directly.
Check Submission Status — Review-PR status for a submitted template: state, labels, CI checks,
reviewer comment count, merged flag.
Revise Submission — Push the draft's current state onto the open review PR (after you edited
steps in response to reviewer feedback).
Withdraw Submission — Withdraw the template from review: closes the PR without merging and
clears the submission state. The draft itself is kept.
Create Approval Request — Ask a human to approve an action before you take it. Parks the request on
the HITL server and surfaces it on the reviewer's phone. Returns the
approval_id — then call wait_for_human_decision(approval_id). risk: low |
medium | high; detail is a free-form object describing the action.
Wait For Human Decision — Block until a human approves or rejects the request, or `timeout` seconds
pass. Returns {status, reason, decided_by}: status is approved | rejected |
timeout. On timeout the request is still pending — call again to keep
waiting.
Log Decision — Record a human verdict on an approval (decision: approve | reject).
Normally the phone WebUI logs this; use it when the decision was made out of
band and you need the audit trail and any waiter to resolve.
Resume Workflow — Fetch the resolved verdict as an actionable directive:
{decision, allow, status, reason}. `allow` is the boolean to gate on —
proceed when true, otherwise stop and surface the reason.
Audit Agent Action — Append an entry to the HITL append-only audit trail — e.g. record an
action you took after approval, tying it back to its approval_id.
MCPBundles probed 19 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.
What authentication does SkillSimm require?
SkillSimm 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.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.