mcp-orchestrator
Skill0 starsChanged 4 months agoMITView on GitHub
Use when a task should be solved through MCP servers, connected tools, or external structured capabilities. Handles server selection, tool discovery, trust-aware invocation order, and result summarization so MCP use is predictable instead of ad hoc.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- cobusgreyling/grok-build-arsenaltheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- cobusgreyling/grok-build-arsenal★ 6same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Show its rules and text
We split this skill into the rules it gives an agent
27 rules. About 0 are common, 23 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈23
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use this skill after deciding that MCP is the right lane.
- Very specific: line 19
if the environment requires tool_search for deferred or MCP tool discovery, use it
- Distinctive: line 20
do not assume generic resource-listing calls are the right discovery path everywhere
- Distinctive: line 23
Prefer read-only or low-scope tools before write-capable tools.
- Distinctive: line 25
Keep a short running model of:
- Distinctive: line 31
If the best MCP path fails, re-check discovery and assumptions once before deciding whether to fall back to a non-MCP path.
- Distinctive: line 36
Prefer connector-native workflows when the user is targeting a connected system.
- Distinctive: line 37
Avoid MCP if local tools can solve the task more simply and safely.
- Distinctive: line 38
Use one MCP tool at a time unless parallelism is clearly independent.
- Distinctive: line 40
If MCP adds friction without better access, correctness, or scope control, do not use it.
- Distinctive: line 45
Prefer specific object-level tools over broad search or admin tools.
- Distinctive: line 46
Avoid sending more user data than the selected tool needs.
- Distinctive: line 47
If a tool schema is unclear, restate the intended arguments before calling it.
- Distinctive: line 48
If a call fails because the tool or server assumptions were wrong, refresh discovery instead of retrying blindly.
- Distinctive: line 49
If a write-capable tool is not clearly needed, stay with read-only inspection.
- Very specific: line 53
Do not use this skill to justify MCP after safe-task-router or direct evidence shows local tools are better.
- Distinctive: line 54
Do not skip discovery and jump straight to a guessed tool call.
- Distinctive: line 55
Do not keep retrying the same failing tool with the same assumptions.
- Distinctive: line 56
Do not combine server selection, trust review, and execution into one opaque step.
- Distinctive: line 61
If a connected Google Drive or GitHub tool provides the exact object you need, MCP is likely the right path.
- Distinctive: line 62
If the answer is already in local files or direct shell inspection, do not route through MCP just because a connector exists.
- Distinctive: line 63
If the first MCP tool only helps you discover a more specific tool, stop and narrow before making broader calls.
- Very specific: line 64
If trust, data exposure, or local execution risk becomes non-trivial, pair with secure-mcp-governor before mutating anything.
- Distinctive: line 68
Treat stdio servers as local code execution surfaces.
- Distinctive: line 69
Treat remote MCP endpoints as external trust boundaries.
- Distinctive: line 70
Do not assume a server is safe just because it is available.
- Distinctive: line 75
Keep the user-facing explanation brief:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
MCP Orchestrator
Use MCP deliberately.
Use this skill after deciding that MCP is the right lane. Pair it with secure-mcp-governor whenever trust, data exposure, or local execution risk is non-trivial.
This skill ends once the correct MCP tool path is chosen, executed, and either verified or intentionally abandoned in favor of a safer non-MCP path.
Workflow
- Determine whether MCP is actually the best path.
- Identify candidate MCP servers relevant to the task.
- Discover available MCP tools using the environment's approved discovery mechanism.
- if the environment requires
tool_searchfor deferred or MCP tool discovery, use it - do not assume generic resource-listing calls are the right discovery path everywhere
- if the environment requires
- Inspect available tools before deciding on a call path.
- Narrow the list to the smallest plausible tools.
- Prefer read-only or low-scope tools before write-capable tools.
- Validate arguments against the tool schema before invocation.
- Keep a short running model of:
- chosen server
- chosen tool
- expected output
- trust level
- Invoke one tool at a time unless calls are truly independent.
- If the best MCP path fails, re-check discovery and assumptions once before deciding whether to fall back to a non-MCP path.
- Summarize results in task language, not just raw MCP output.
Selection Rules
- Prefer connector-native workflows when the user is targeting a connected system.
- Avoid MCP if local tools can solve the task more simply and safely.
- Use one MCP tool at a time unless parallelism is clearly independent.
- Re-check available tools when the server context changes.
- If MCP adds friction without better access, correctness, or scope control, do not use it.
Call Discipline
- List or inspect before mutate.
- Prefer specific object-level tools over broad search or admin tools.
- Avoid sending more user data than the selected tool needs.
- If a tool schema is unclear, restate the intended arguments before calling it.
- If a call fails because the tool or server assumptions were wrong, refresh discovery instead of retrying blindly.
- If a write-capable tool is not clearly needed, stay with read-only inspection.
Boundary Rules
- Do not use this skill to justify MCP after
safe-task-routeror direct evidence shows local tools are better. - Do not skip discovery and jump straight to a guessed tool call.
- Do not keep retrying the same failing tool with the same assumptions.
- Do not combine server selection, trust review, and execution into one opaque step.
- Re-route out of MCP if discovery shows no tool with a clear advantage for the task.
Boundary Examples
- If a connected Google Drive or GitHub tool provides the exact object you need, MCP is likely the right path.
- If the answer is already in local files or direct shell inspection, do not route through MCP just because a connector exists.
- If the first MCP tool only helps you discover a more specific tool, stop and narrow before making broader calls.
- If trust, data exposure, or local execution risk becomes non-trivial, pair with
secure-mcp-governorbefore mutating anything.
Trust-Aware Operation
- Treat stdio servers as local code execution surfaces.
- Treat remote MCP endpoints as external trust boundaries.
- Do not assume a server is safe just because it is available.
- Pair this skill with
secure-mcp-governorwhenever trust is not trivial.
Output
Keep the user-facing explanation brief:
- why MCP was chosen
- which server/tool was used
- what came back
- what the next best action is
Example:
- why MCP was chosen: the task depends on a connected system that local files cannot access
- which server/tool was used: selected the Google Drive server and a file-specific read tool
- what came back: the target file metadata and current contents
- what the next best action is: continue with a narrower read or switch back to local work if MCP is no longer needed
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

