Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Copilot Studio MCP

NPM · COPILOT-STUDIO-MCP · SCANNED SEP 20

Build, test, ship and maintain Microsoft Copilot Studio agents from the editor

Available components

+4 this week 72 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 60 of 157 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability76
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 34022 tokens (~239/item across 142 items; 142 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management30
  • Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage95
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 85% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 16 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "cs_logout" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 143 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Copilot Studio MCP server?

Copilot Studio MCP runs locally as an npm package, launched with npx -y copilot-studio-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · copilot-studio-mcp

# add to Claude Code
claude mcp add jgt87-copilot-studio-mcp -- npx -y copilot-studio-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "jgt87-copilot-studio-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "copilot-studio-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "jgt87-copilot-studio-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "copilot-studio-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add jgt87-copilot-studio-mcp -- npx -y copilot-studio-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jgt87-copilot-studio-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "copilot-studio-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add jgt87-copilot-studio-mcp --command npx --arg -y --arg copilot-studio-mcp
# ~/.hermes/config.yaml
mcp_servers:
  jgt87-copilot-studio-mcp:
    command: "npx"
    args: ["-y", "copilot-studio-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "jgt87-copilot-studio-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "copilot-studio-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add jgt87-copilot-studio-mcp -t stdio -c npx -a -y copilot-studio-mcp
// mcp.json
{
  "mcpServers": {
    "jgt87-copilot-studio-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "copilot-studio-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 0
    • Security disclosure: unverified → fail functional
  • 16 Sept 26 +1
    • Security disclosure: fail → unverified functional
  • 15 Sept 26 +15
    • Malware scan: unverified → pass security
  • 14 Sept 26 −13
    • Malware scan: pass → unverified security
    • Tool safety: pass → unverified security
    • Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
    • Schema quality: 100 → unverified functional
    • Stability: unverified → 0.10 functional
    • Package version: 0.1.6 → 0.1.7 functional
  • 13 Sept 26 +15
    • Malware scan: unverified → pass security
  • 11 Sept 26 53

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/copilot-studio-mcp@0.1.7

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 157 packages
Packages resolved 157
Deprecated 1
Stale 59
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 142 exposed · ~33,335 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
cs_sync_solution ~312

Re-export the solution and update an existing unpacked solution folder or .cdsproj with the environment's current state. Read-only for the environment. Runs 'pac solution sync' with the active pac auth profile.

NameTypeReqDescription
asyncbooleanRun the operation asynchronously
backgroundbooleanRun in the background and return a jobId immediately, for a command that takes longer than the client will wait. Poll cs_job_status.
cwdstringWorking directory for pac (for project commands: the solution project folder)
environmentstringEnvironment id or URL; default: the environment of the active pac auth profile
includestringSettings to include in the export (pac solution export --include values)
localizebooleanExtract string resources into .resx files
mapstringMapping XML file for component folders
maxAsyncWaitTimenumberMax asynchronous wait time in minutes (default 60)
packageTypestringUnmanaged, Managed or Both (default Both)
profilestringpac auth profile to run as: the admin account for tenant commands. Defaults to CPS_ADMIN_PROFILE for admin commands and CPS_PAC_PROFILE otherwise, then the active profile. cs_init lists the profiles.
solutionFolderstringUnpacked solution folder (Other/Solution.xml root) or .cdsproj folder; default: cwd
timeoutSecondsnumberDefault 3600

No output schema declared.

No examples provided.

cs_test_set_from_transcripts ~316

Write the portal's import CSV from questions people actually asked, most frequent first, instead of guessing from the workspace. onlyFailed (default true) keeps the sessions that escalated, went unanswered or were abandoned, which are the ones worth turning into regression cases. Read-only apart from writing the file; import it once in the portal, then cs_run_evaluation automates the runs.

NameTypeReqDescription
botIdstringAgent (bot) id. Defaults to workspace sync metadata or CPS_AGENT_ID.
clientIdstringEntra app (client) id for MSAL. Defaults to CPS_CLIENT_ID, then the first-party VS Code id.
daysnumberOnly sessions from the last N days
environmentIdstringPower Platform environment id (GUID). Defaults to workspace sync metadata or CPS_ENVIRONMENT_ID.
maxCasesnumberMaximum cases in the CSV (portal limit is 100)
onlyFailedbooleanDefault true: only sessions that escalated, went unresolved or were abandoned
outputPathstringDefault <workspace>/../<agent>-transcript-testset.csv
tenantIdstringEntra tenant id. Defaults to the workspace sync metadata, then CPS_TENANT_ID.
topnumberMaximum sessions to read (default 100, max 500)
workspacestringPath to (or inside) the agent workspace. Defaults to CPS_WORKSPACE or the current directory.

No output schema declared.

No examples provided.

cs_update_agent ~508

Edit agent.mcs.yml (standard harness): instructions, display name, conversation starters, model hint, and the settings the portal groups under responses and generative AI: response instructions (wording and formatting), response mode, conversation history, capability toggles (web browsing, code interpreter, image generation, Teams / SharePoint / email / meeting / people search), whether the model may use its own general knowledge, content moderation level, file analysis and semantic search. The first call writes nothing: it returns the change - the current lines against the proposed ones, and the instruction character count against the 8000 the product allows - and the file is written on a second call with confirm: true. Local file change; cs_push applies it. For GitHub Copilot harness (cli-copilot) workspaces the instructions go into settings.mcs.yml.

NameTypeReqDescription
addConversationStartersarray
appendInstructionsstringAdd a paragraph to the instructions
appendResponseInstructionsstringAdd a line to the response formatting, within the same 500 characters
capabilitiesobjectCapability toggles; only the ones you pass are changed
confirmbooleanRequired to write the change to the file. Without it the tool returns a preview - the changed lines against the current ones, and the character count - and writes nothing.
contentModerationstring
conversationStartersarray
defaultResponseModestringResponse mode: Auto, ThinkDeeper (more reasoning, slower) or QuickResponse
displayNamestring
historystringWhether the agent sees conversation history
historyMessagesnumberHow many past user messages to include (with history: conversation)
instructionsstringReplace the instructions
isFileAnalysisEnabledboolean
isSemanticSearchEnabledboolean
modelNameHintstringModel hint, e.g. GPT5Chat
responseInstructionsstringHow answers should be worded and formatted (Settings > Responses > Response formatting in the portal), separate from the main instructions. Capped at 500 characters.
useModelKnowledgebooleanWhether the model may answer from its own general knowledge as well as the knowledge sources
workspacestringPath to (or inside) the agent workspace. Defaults to CPS_WORKSPACE or the current directory.

No output schema declared.

No examples provided.

cs_update_connection ~274

Rotate the app registration or secret behind a service-principal Dataverse connection. Runs 'pac connection update' with the active pac auth profile. Mutates a live environment: requires confirm: true (a dry run otherwise).

NameTypeReqDescription
applicationIdstringyesApp registration (client) id
backgroundbooleanRun in the background and return a jobId immediately, for a command that takes longer than the client will wait. Poll cs_job_status.
clientSecretstringyesNew client secret (masked in logs) (masked in logs and results)
confirmbooleanRequired to actually perform a change in a live environment. Without it the tool returns a dry run.
connectionIdstringyesConnection id (cs_list_connections)
cwdstringWorking directory for pac (for project commands: the solution project folder)
environmentstringEnvironment id or URL; default: the environment of the active pac auth profile
profilestringpac auth profile to run as: the admin account for tenant commands. Defaults to CPS_ADMIN_PROFILE for admin commands and CPS_PAC_PROFILE otherwise, then the active profile. cs_init lists the profiles.
tenantIdstringyesEntra tenant id
timeoutSecondsnumberDefault 600

No output schema declared.

No examples provided.

cs_update_flow ~435

Change a flow's name, description or definition in the environment. Pass 'steps' (and optionally 'trigger') to rebuild the definition the way cs_build_flow_definition does, or 'definition' for a ready-made one; either replaces properties.definition inside the existing clientdata and keeps the connection references. 'clientData' replaces the whole document. Read the current one with cs_get_flow includeDefinition first. Managed flows cannot be edited in place; edit them in their source environment or through a solution. Changes a live environment: requires confirm: true.

NameTypeReqDescription
clientDataobjectThe whole clientdata document; overrides 'definition'
clientIdstringEntra app (client) id for MSAL. Defaults to CPS_CLIENT_ID, then the first-party VS Code id.
confirmbooleanRequired to actually perform a change in a live environment. Without it the tool returns a dry run.
connectionReferencePrefixstringPrefix for generated connection reference names, usually your publisher prefix
connectionReferencesobjectConnection reference entries to add or explicitly replace; existing entries are otherwise preserved
dataverseUrlstringDataverse URL; default: from the workspace or the environment
definitionobjectPower Automate definition object (properties.definition), instead of steps
descriptionstring
environmentIdstringPower Platform environment id (GUID). Defaults to workspace sync metadata or CPS_ENVIRONMENT_ID.
flowIdstringyesFlow (workflow) id
namestring
outputsarrayWhat the flow answers with (agent-callable and HTTP flows)
stepsarraySteps in order; each waits for the previous one to succeed
tenantIdstringEntra tenant id. Defaults to the workspace sync metadata, then CPS_TENANT_ID.
triggerDefault: 'agent' (When an agent calls the flow)
workspacestringPath to (or inside) the agent workspace. Defaults to CPS_WORKSPACE or the current directory.

No output schema declared.

No examples provided.

cs_update_settings ~161

Set values in settings.mcs.yml by dot path, e.g. {"configuration.settings.GenerativeActionsEnabled": true}. Do not change authoringModel/recognizer/template. The first call changes nothing: it returns the files it would write, as a diff against what is there now, for the user to approve. Call it again with the same arguments plus confirm: true to write them.

NameTypeReqDescription
confirmbooleanRequired to write the change to the file. Without it the tool returns a preview - the changed lines against the current ones, and the character count - and writes nothing.
patchobjectyes
workspacestringPath to (or inside) the agent workspace. Defaults to CPS_WORKSPACE or the current directory.

No output schema declared.

No examples provided.

cs_upgrade_solution ~270

Complete a managed solution upgrade that was imported as a staged upgrade (pac solution import --stage-and-upgrade or the portal's 'Stage for upgrade'). Runs 'pac solution upgrade' with the active pac auth profile. Mutates a live environment: requires confirm: true (a dry run otherwise).

NameTypeReqDescription
asyncbooleanRun the operation asynchronously
backgroundbooleanRun in the background and return a jobId immediately, for a command that takes longer than the client will wait. Poll cs_job_status.
confirmbooleanRequired to actually perform a change in a live environment. Without it the tool returns a dry run.
cwdstringWorking directory for pac (for project commands: the solution project folder)
environmentstringEnvironment id or URL; default: the environment of the active pac auth profile
maxAsyncWaitTimenumberMax asynchronous wait time in minutes (default 60)
profilestringpac auth profile to run as: the admin account for tenant commands. Defaults to CPS_ADMIN_PROFILE for admin commands and CPS_PAC_PROFILE otherwise, then the active profile. cs_init lists the profiles.
solutionNamestringyesSolution unique name
timeoutSecondsnumberDefault 3600

No output schema declared.

No examples provided.

cs_validate ~124

Structural validation of every component file against the Copilot Studio authoring schema (kinds, unknown/missing properties, duplicate ids, placeholders, Power Fx prefixes, variable scopes) plus cross-file checks (connection references, topic redirects). Answers 'is anything broken in these files?'; it only reads them and sends nothing anywhere. cs_push runs it itself and blocks on errors.

NameTypeReqDescription
filestringValidate a single file (relative to workspace)
workspacestringPath to (or inside) the agent workspace. Defaults to CPS_WORKSPACE or the current directory.

No output schema declared.

No examples provided.

Common questions

What is the Copilot Studio MCP server?

Copilot Studio MCP is listed in the public MCP registry as io.github.jgt87/copilot-studio-mcp. Build, test, ship and maintain Microsoft Copilot Studio agents from the editor. This page covers its npm package (copilot-studio-mcp).

Is the Copilot Studio MCP server safe to use?

Copilot Studio MCP scores 72 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Copilot Studio MCP server expose?

Copilot Studio MCP exposes 142 tools: cs_init, cs_login, cs_login_status, cs_logout, cs_set_tool_preset, and 137 more. Their descriptions and schemas cost roughly 33,335 tokens of context every time the server is loaded.

Is the Copilot Studio MCP server still maintained?

Copilot Studio MCP is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Copilot Studio MCP server under?

Copilot Studio MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.