Copilot Studio MCP Server

Copilot Studio MCP

An MCP server that lets a coding agent (GitHub Copilot in VS Code, Claude Code, or any other MCP client) build, test, ship and look after Microsoft Copilot Studio agents from the editor.

An agent becomes a folder of YAML you can read, diff and commit. The server writes that folder the way the Copilot Studio VS Code extension does, syncs it with the live agent through the official Power Platform CLI (pac), and calls the Power Platform, Dataverse, BAP, Power Automate and DirectLine APIs for what the CLI does not cover: evaluations, chat, cloud flows, portal drift, transcripts. Nothing reaches a live environment without your approval, and when a choice is still open the tool asks a question instead of failing.

What you can do with it

The complete tool list is in docs/tools.md and the diagrams in docs/flows.md; both ship inside the npm package under docs/. The reference sections at the end of this page cover the agent settings the server can write, authentication and permissions, configuration, the hard limits and how this differs from pac's own MCP server.

Status

Early release. What has actually been exercised:

• Offline: 251 unit tests over the compiled output, plus a pack oracle that round-trips every authoring tool's YAML through pac copilot init and pac copilot pack.
• Against a real tenant (2026-09-08, phases A to F of docs/live-verification.md): the connector registry, the pac connection list layout, pac copilot clone and its sync metadata, drift detection and the cs_push conflict refusal, and the evaluation path end to end including the portal's CSV import format and the metric status strings. A portal-made agent validates clean, so cs_validate produces no false positives on real content. That run also caught a real bug: pac copilot publish prints "Failed to publish" and exits 0, so a failed publish was being reported as a success. Fixed.
• Not yet verified live: the transcript tools, cs_check_drift in quick mode, cs_chat, the Dataverse listBots path, moving a solution between environments, and every flow the flow builder produces (none has been imported into an environment yet).

docs/verify.md is the short list of what is still open, docs/STATUS.md the full record. Read the dry run before confirming anything that writes.

Set up

Prerequisites

• Node.js 20+.
• .NET 10 SDK and the Power Platform CLI: dotnet tool install --global Microsoft.PowerApps.CLI.Tool. If the SDK lives in your user profile, set DOTNET_ROOT to that folder; the server defaults it to ~/.dotnet when that folder exists.
• A pac auth profile for the environment you work in, created once in a terminal: pac auth create --environment <id or URL>. Everything that goes through pac (create, clone, pull, push, publish, solutions, administration) uses it, with Microsoft's own first-party app.
• For the API-based tools (environments, evaluations, chat, flows, drift, transcripts): an Entra sign-in through cs_login, done from the session. By default no app registration is needed; Authentication and app registration says when you need one and which permissions it must carry.

Install and register

The server is on npm as copilot-studio-mcp, so the usual install is no install: point your MCP client at npx, and the first start fetches the package.

There is also a VS Code extension, vscode-extension/, which registers the server with VS Code's MCP host and exposes the environment variables below as settings. It carries the server and its dependencies inside the VSIX, so it needs no npm and no network on first start. Build it with cd vscode-extension && npm install && npm run package; install the resulting .vsix with code --install-extension copilot-studio-mcp-<version>.vsix.

VS Code, from a terminal or by hand in .vscode/mcp.json (workspace) or the user-level mcp.json:

code --add-mcp '{"name":"copilot-studio","command":"npx","args":["-y","copilot-studio-mcp"]}'

{
  "servers": {
    "copilot-studio": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "copilot-studio-mcp"],
      "env": { "CPS_WORKSPACE": "${workspaceFolder}" }
    }
  }
}

Claude Code (user scope):

claude mcp add-json copilot-studio '{"type":"stdio","command":"npx","args":["-y","copilot-studio-mcp"]}' --scope user

Mistral Vibe, in ~/.vibe/config.toml (or $VIBE_HOME/config.toml; a ./.vibe/config.toml in the working folder takes precedence). Vibe gives a server 10 seconds to start by default, which a first npx fetch on a corporate network can exceed, so install globally and run the entry point with node (find the folder with npm root -g). On Windows, keep paths in single quotes: TOML reads backslashes inside double quotes as escapes, and "C:\Users\..." is not valid TOML.

[[mcp_servers]]
name = "copilot-studio"
transport = "stdio"
command = "node"
args = ['C:\Users\<you>\AppData\Roaming\npm\node_modules\copilot-studio-mcp\dist\index.js']
startup_timeout_sec = 60   # default 10
tool_timeout_sec = 300     # default 60; solution exports and evaluation runs take longer

npm install -g copilot-studio-mcp with "command": "copilot-studio-mcp" avoids the npx start-up cost. The server is published to the MCP Registry as io.github.jgt87/copilot-studio-mcp, which is what VS Code's MCP gallery (Extensions view, search @mcp) draws from through the GitHub MCP Registry. To run from a clone instead, see Development.

Environment variables are optional and listed under Configuration.

The first session

1. cs_init. Reports pac and .NET, the pac profiles and which one is active, the MSAL sign-in, the write policy in force, the workspace it found and the next steps for it. It also returns a menu of tool presets; on a smaller model pick one (see Running on a smaller model).
2. cs_login when a cloud tool needs it. The call opens the browser from the server and returns within 15 seconds; if the sign-in has not finished by then it returns status: pending with the URL so you can open it yourself, and the next cloud call (or cs_login_status) picks the token up. That is what makes sign-in work from clients that cap tool-call duration or run the server where no browser can be launched. Device code (mode: device_code) is the alternative where the tenant allows it; many block it by Conditional Access policy.
3. cs_guide <topic> when you want the walkthrough for one job rather than inventing a sequence: getting-started, instructions, knowledge, tools, topics, evaluations, publish-and-test, drift, transcripts, solutions, administration, troubleshooting. Each names the tool per step, the portal steps that cannot be automated, and the next steps for your workspace. Six MCP prompts (new agent, add knowledge, add tool, write instructions, review and push, check drift) wrap the same walkthroughs in clients that show prompts as commands.

Approval before anything changes

The server never changes a live Copilot Studio environment on its own. Every tool that can (cs_push, cs_publish, cs_run_evaluation, cs_import_solution, cs_deploy_solution, cs_create_agent with an environment, the delete tools, the flow and admin tools that write, and the environment-changing pac wrappers) returns a dry run describing what it would do, and does nothing else, until it is called again with confirm: true. The calling agent is instructed, in the MCP handshake, to show that dry run and pass confirm only after you agree; one approval covers one call.

Changing the agent on disk asks the same way, for the same reason: an edit you did not intend is cheap to make and expensive to notice. cs_add_topic, cs_add_knowledge_source, cs_add_tool, cs_add_flow, cs_add_trigger, cs_add_variable, cs_edit_topic, cs_edit_tool, cs_edit_knowledge, cs_update_settings, cs_update_agent and cs_generate_instructions write nothing on the first call. They return the change instead - a file that would be created shown in full, a file that would be edited shown as a diff against what is there now - and write it when the same call is repeated with confirm: true. Reviewing, validating and describing read only, and ask nothing.

The prose fields get their own accounting, because they are the change a diff alone does not settle: the preview carries the character count and how much of the product's limit is left, and an edit that would exceed it is refused outright rather than failing at push time. The limits are not the same - instructions holds 8000 characters, and the Settings > Responses > "Response formatting" box (responseInstructions) only 500.

For a hard lock, set CPS_READ_ONLY=1 in the server's environment: the environment-changing tools are then not registered at all, so no confirmation can reach the environment, while authoring, validation, review and the read-only tools keep working. cs_init reports the mode and which tools are withheld. test/policy.test.js fails if a tool that declares confirm is missing from that list, so the two layers cannot drift apart.

Three more behaviours you will meet in every workflow:

• A question instead of an error. When a call cannot proceed because something has not been decided (which connector, which operation, which agent), the tool returns needsInput: true with what it needs, why, the real choices when the server can list them, and the tool that lists more. Nothing is written; the calling agent asks you and calls again. This works in every client, including those without MCP elicitation.
• Long calls run in the background. MCP clients cap a tool call at about a minute. Tools that can run longer (cs_pull_solution, cs_create_auth_profile, environment provisioning, every pac wrapper) accept background: true, return a jobId at once, and cs_job_status reports the phases and the result from an on-disk record that survives a server restart. A tool decides whether it may change anything before it starts a job, so the confirm contract is unaffected.
• Writes are never retried. A read that fails on a transport error or a 429/5xx is retried with backoff and honours Retry-After; a publish or an import that timed out may already have been applied, so it is reported, not repeated.

Two accounts: maker and admin

Making agents and administering the tenant are usually different accounts. pac keeps one active authentication profile per machine, so create one profile per account and let the server switch:

pac auth create --name maker --environment <environment id or url>
pac auth create --name admin --environment <environment id or url>

Or from the session: cs_create_auth_profile with name, environment and background: true, because pac opens its own browser and waits for the sign-in (cs_job_status reports when the profile exists). cs_list_auth_profiles shows the profiles and which is active.

Core sync and solution tools use CPS_PAC_PROFILE; admin commands and tenant backup use CPS_ADMIN_PROFILE; every pac wrapper and cs_pac also accept an explicit profile. When the server selects a profile it restores the previous one afterwards, and every pac call in the process shares one queue, so multi-step operations (bootstrap, solution pull and deploy, snapshots) hold the profile for the whole run. Other server instances and terminal pac commands are outside that coordination. The MSAL sign-in used by the API-based tools is separate again and independent of pac.

Build a new agent

From an empty folder to a published agent you can talk to. Each step is one tool call; the steps that change the environment show a dry run first.

1. Pick the environment. cs_list_environments (needs cs_login), or take the environment id from the Copilot Studio URL.

2. Pick or create the solution. cs_list_solutions shows what exists; an existing solution works as long as it is unmanaged and you use its publisher prefix. To start a solution for your agents: cs_create_solution uniqueName=contoso_Agents publisherPrefix=contoso confirm=true. The solution is the unit you later export and import to move the agent to test and production, so it is worth choosing rather than letting one be created per agent.

3. Create the agent inside it. cs_create_agent name="Contoso Support" publisherPrefix=contoso projectDir=./contoso-support environment=<id> solutionName=contoso_Agents confirm=true (add createSolution=true to fold step 2 in). The server scaffolds locally with pac copilot init, packs with the solution name, imports, then clones the live agent back so projectDir is a sync-connected workspace with the default system topics. Without environment you get a local scaffold only, which can pack settings, agent and topics but not knowledge, tools or flows.

   Leave out publisherPrefix or projectDir and the tool asks instead of guessing, listing the publishers in the environment (and, when you named a solution, the one prefix that solution's publisher allows) and suggesting a folder named after the agent. The prefix is worth the question: it becomes part of the schema name of every component the agent will ever have (contoso_contososupport.topic.Greeting), it cannot be changed afterwards without recreating them, and it has to match the publisher of the solution the agent lands in.

4. Say what the agent is for. cs_generate_instructions purpose="Answer IT questions and create ServiceNow tickets" audience="Employees" tone="Friendly, brief" boundaries=["never reset passwords"] modelName="Agent instructions" drafts the instructions with an AI Builder prompt (cs_list_prompts shows the prompts in the environment; create a "write agent instructions" prompt once in AI Builder if you have none). Review the draft, call again with apply=true to write it into agent.mcs.yml; later refine=true with a changeRequest revises what is there. Or write them yourself with cs_update_agent, which also sets response instructions and mode, conversation history, capabilities, moderation, model and conversation starters (the full map).

5. Give it something to work with. cs_add_knowledge_source for a public website, SharePoint, a Graph connector or uploaded files; cs_add_topic for deterministic conversations built from trigger phrases plus message, question, condition, set-variable, redirect, HTTP, flow, generative answers (optionally scoped to named knowledge sources), adaptive card, transfer and end nodes; cs_add_tool for anything the agent should call (the tools workflow). cs_add_trigger and cs_add_variable cover event triggers and global variables.

6. Review and validate. cs_review_agent is a rules-based read of the whole workspace with a 10-point score: missing escalation or fallback, weak tool descriptions, overlapping trigger phrases, private knowledge with no authentication, secrets in files. Each finding names the rule and the fix. cs_validate then checks every file against the authoring schema (744 definitions) and across files: connection references that nothing binds, catalog operations that do not exist, redirects to topics that are not there. It also blocks on the mistakes that a push accepts without complaint and then stores wrongly: merge-conflict markers left by a pull (the push keeps only the text before them), leftover <AGENT_SCHEMA> placeholders, file and schema names pac rejects, and more than 200 trigger phrases. It warns about text cut off by an unquoted #, nodes after an end node, formulas missing their =, adaptive cards without a submit action, and topic names with a period, which stop the solution from exporting.

7. Push. cs_push confirm=true is the portal's Save: the draft agent now shows your topics, knowledge and tools. The dry run runs validation and the quick drift check first, and the push is refused when a colleague changed the same component in the portal since your last pull. Tools with a connection reference need one portal step: open the tool under the agent's Tools, Connect, then cs_pull to bring the binding down.

8. Publish and talk to it. cs_publish confirm=true, then cs_chat utterance="my laptop is slow". The testing workflow turns that into repeatable checks.

flowchart TD
    A["cs_init"] --> B["cs_list_solutions<br/>pick one, or cs_create_solution"]
    B --> C["cs_create_agent<br/>environment + solutionName + confirm"]
    C --> D["cs_generate_instructions<br/>AI Builder prompt, then apply"]
    D --> E["cs_add_topic / cs_add_knowledge_source / cs_add_tool<br/>(cs_list_connectors, cs_describe_connector)"]
    E --> R["cs_review_agent"]
    R --> H["cs_validate"]
    H -- errors --> E
    H -- clean --> I["cs_push confirm"]
    I --> J{"tool needs a connection?"}
    J -- yes --> J1["portal: authorise once"] --> J2["cs_pull"] --> K
    J -- no --> K["cs_publish confirm"]
    K --> L["cs_chat"]

GitHub Copilot harness agents (cs_create_agent with authoringMode: cli-copilot) are a smaller surface: init, pack, import, instructions and chat. Topics and evaluations are standard-harness features.

Work on an existing agent

Most agents already exist, often made in the portal. The loop is clone, change, review, merge, push.

1. Clone it. cs_list_agents (through pac or Dataverse), then cs_clone_agent bot=<id or schema name> outputDir=./support-agent. The result is a sync-connected workspace with agent.mcs.yml, settings.mcs.yml, topics/, knowledge/, actions/, trigger/, variables/, workflows/ and the connection references. cs_describe_workspace inventories it and ends with next steps.
2. Change it. Components are found by name, file stem or path. cs_edit_topic changes trigger phrases, priority and nodes (by position or id); cs_edit_tool changes descriptions, inputs and the connection; cs_edit_knowledge changes a site or a trigger condition; cs_remove_component deletes a topic, knowledge source, tool, trigger or variable and prunes the connection reference nothing else uses, noting any redirect left dangling. cs_update_agent and cs_update_settings cover the agent's own settings. Adding works as in the new-agent flow. Every edit keeps the file header the extension expects.
3. Review and merge. cs_review_agent, then cs_pull to bring down what colleagues changed in the portal (pac's three-way merge), then cs_validate.
4. Push. cs_push confirm=true. If a portal change and a local edit touch the same component the push is blocked; cs_pull resolves it, force: true overrides it.
5. Commit. Keep the workspace in git and commit after every pull (the tool result reminds you). Portal drift then shows up as a diff you can review: accepting it is a commit, rejecting it is a push of the local version.

Around that loop: cs_delete_agent and cs_delete_solution remove things from the environment (confirm); cs_extract_agent_template and cs_create_agent_from_template turn one agent into a template for more; cs_extract_translations and cs_merge_translations do the localisation round trip (.resx or .json, with whatIf); cs_quarantine_agent takes an agent out of service and back.

Give the agent tools

Copilot Studio agents can call any connector in the environment (more than a thousand Microsoft-published ones plus custom connectors), MCP servers exposed through connectors, cloud flows, AI Builder prompts, other agents, and a few rarer kinds. The server knows the kinds from the YAML schema and the instances from the environment, which is the only source that knows what exists there.

1. Find the connector. cs_list_connectors search=ServiceNow lists the environment's connector registry, the same list the portal's Add a tool shows, with MCP servers flagged. Without a sign-in it falls back to an offline seed generated from the public connector reference (display name to shared_ id, no operations): a starting point, not proof the connector is enabled for you.
2. Find the operation. cs_describe_connector connector=shared_service-now operation=incident turns the connector's OpenAPI definition into operations with operationId, required and optional parameters and response fields; x-ms-agentic-protocol: mcp-streamable-1.0 marks MCP endpoints. Definitions are cached under .cs-catalog/<environment>/ so later calls are offline.
3. Add the tool. cs_add_tool takes a typed spec for a connector action, an MCP server, a cloud flow, an AI Builder prompt (cs_list_prompts shows them), a connected agent or a child agent, and a raw type for the rest (AI plugin, Bot Framework skill, client action, computer-use agent). With the definition cached it checks the operationId, fills the automatic inputs from the operation's required parameters, and writes the YAML under actions/ plus a connection-reference stub. If you have not named a connector or operation yet the call comes back as a question with the ranked candidates.
4. Connect it, once, in the portal. A connection is an authorised link that only the portal can create (the one exception is a service-principal Dataverse connection, which cs_create_connection makes). After cs_push, open the tool under the agent's Tools, Connect, then cs_pull. cs_validate warns about tool files whose operation is not in the cached definition, and cs_review_agent flags tools whose description will not let the orchestrator pick them.

A unit test compares the schema's list of tool kinds with the server's table, so a schema update that introduces a new kind fails the build until the kind is classified. Flows as tools are either a scaffold (cs_add_flow, experimental) or a real flow built with the flow builder and referenced from the agent.

Publish and test

1. Publish. cs_publish confirm=true is the Publish button, through pac copilot publish or the Dataverse PvaPublish action polled until publishedon moves.

2. Chat. cs_chat utterance="..." sends one utterance to the published agent and returns the reply; pass the conversationId back for the next turn. With transport: auto the server reads the agent's authentication mode: no-auth and manual-auth agents go through DirectLine (the token endpoint of a published agent is anonymous, so no app is needed); an agent with integrated Entra authentication goes through the Copilot Studio client SDK and needs your own app id with the CopilotStudio.Copilots.Invoke scope (clientId, or CPS_CLIENT_ID).

3. Make it repeatable. cs_run_conversation_tests runs a YAML file of utterances and expectations through the same chat path and reports what failed. Expectations cover the wording and what the agent did: usedTool, notUsedTool, usedTopic, notUsedTopic and citedKnowledge read the topic, tool and knowledge attribution from the activities, so a test can tell a real tool call from an answer that merely reads correctly. Every result, and every cs_chat reply, reports the observed topic, tool and citations; an expectation that cannot be judged (no attribution in the activities) says so rather than failing the agent. The attribution key names come from documentation and are unverified live; docs/test-verification.md is the runbook that settles them.

4. Evaluate. The portal's Evaluation feature runs a test set of questions against the agent and scores each answer. The one thing its API cannot do is create the test set, so the loop is:

   • cs_create_test_set_csv suggestFromWorkspace=true writes the CSV in the portal's import format (max 100 cases), seeded from your topics and knowledge.
   • Import it once in the portal's Evaluation tab.
   • cs_list_test_sets, then cs_run_evaluation confirm=true wait=true, then cs_get_evaluation_run for per-case results with pass and fail buckets; cs_list_evaluation_runs for the history.

flowchart TD
    A["cs_create_test_set_csv"] --> B["portal: Evaluation > Import CSV"]
    B --> C["cs_list_test_sets"] --> D["cs_run_evaluation confirm wait"]
    D --> E["cs_get_evaluation_run"] --> F{"failures?"}
    F -- yes --> G["fix topics / instructions / knowledge"] --> H["cs_push confirm"] --> D
    F -- no --> I["cs_publish confirm"]

Learn from production conversations

Once people use the agent, the transcripts are the best source of test cases and of the questions it cannot answer. Copilot Studio stores every session in the Dataverse conversationtranscript table; the server reads it and never writes.

• cs_list_transcripts lists sessions in a window: when, how many turns, the first question, the topics and tools that fired, how it ended.
• cs_get_transcript returns one session's full turn list with the topic and tool attributed to each turn.
• cs_summarize_transcripts aggregates a window: outcomes, escalation rate, sessions that matched no topic, the top topics and tools, and the questions behind the failures.
• cs_test_set_from_transcripts builds the Evaluation import CSV from questions people actually asked, failures first, so the next evaluation run covers what went wrong.

Copilot Studio does not report whether a conversation succeeded. The outcome is this server's reading of the transcript (an escalation, the agent saying it could not answer, a user turn with no reply); resolved means nothing marked the session as failed, not that the user was satisfied. Every result repeats that caveat, and cs_guide transcripts walks the loop from a summary to one transcript to a regression test set. Transcripts hold what users said to the agent, so the signed-in user needs a role that grants read on that table and results are customer data. Unverified against a live tenant.

Keep the workspace and the portal in sync

Makers can keep editing an agent in Copilot Studio after it was cloned; nothing stops them and the platform sends no notification. Every portal edit lands in Dataverse rows: the bot row for settings and instructions, and one botcomponent row per topic, knowledge source, tool, trigger and variable, each with a modified-on stamp and the user who changed it. The server uses those rows to see drift without a re-scan, and a clone to confirm it when the details matter.

1. Sync stamp. cs_clone_agent, cs_pull, cs_push and cs_create_agent (with environment) write .mcs/cs-sync.json: a fingerprint of every workspace file and, when a Dataverse sign-in is cached, the modified-on stamp of every component. cs_describe_workspace shows the last sync.
2. Quick check. cs_check_drift (default mode: quick) reads the bot row and its component rows and compares them with the stamp: which components were modified, added or removed in the portal, by whom and when, whether the agent settings changed, and whether the live agent has unpublished changes. Each component is mapped to its workspace file; when that file also changed locally the entry is a conflict. Seconds, no pac; needs cs_login.
3. Full check. cs_check_drift mode=full runs pac copilot clone into a temporary folder and classifies every file three ways against the stamp: local-modified, remote-modified, both-modified (conflict), added or deleted on either side, with unified diffs. Use it when the quick check reports drift and you want the exact content, or when there is no Dataverse sign-in (only the pac profile is needed). Uploaded knowledge files are covered here, not in the quick check.
4. Push preflight. The cs_push dry run includes the quick check, so the caller sees "three components changed in Copilot Studio since your last pull" before confirming. With confirm, the push is blocked when a portal change and a local edit touch the same component; cs_pull (pac's three-way merge) resolves it and force: true overrides it.
5. Git as the ledger. Commit after every cs_pull; cs_check_drift reports whether the workspace is in a repository and how many of its files are uncommitted.

Limits. The quick check does not see connections (a maker connecting a tool is expected, and connection ids are ignored in every comparison), uploaded knowledge files, channel configuration or the security group. When the stamp has no per-component baseline (no Dataverse sign-in at sync time) it falls back to the sync time with a two-minute margin, so edits made right after a sync count as the sync itself. The component query has not been verified against a live environment yet; see docs/STATUS.md.

Build cloud flows

Flows are built from a step spec, the way topics are, so you do not have to write Logic Apps JSON by hand. cs_build_flow_definition composes the definition locally and returns it together with the connection references it needs; cs_create_flow takes the same spec and creates the flow in an environment or a solution; cs_update_flow takes it and replaces the definition of an existing unmanaged flow, keeping its connection references.

A spec is a trigger plus steps that run in order:

The builder chains runAfter so each step waits for the previous one, normalises action names the way Power Automate does, and collects one connection reference per connector used, reusing it across steps. Expressions are Logic Apps expressions, not Power Fx: @{triggerBody()?['orderId']}, @body('List_rows')?['value']. Connector ids and operation ids come from cs_list_connectors and cs_describe_connector; an operation's parameters are exactly the parameters of a connector step.

Around the builder: cs_list_flows shows the flows in the environment with state, owner and connection references; cs_get_flow returns one with its full definition; cs_delete_flow removes one for good; cs_list_flow_runs, cs_get_flow_run and cs_run_flow read the run history and start a manual run through the Power Automate service (a separate sign-in, cs_login scope='flow'; the signed-in user must own or co-own the flow).

Bind the connections. A connection reference names a connector; a connection is one person's authorised account for it, and until the two are joined the flow cannot run. cs_bind_flow_connection joins them: with one reference and one usable connection it needs nothing but the flow id, and it asks which when there is a choice. It writes whichever of the two shapes the flow uses - a flow built outside a solution names its connection directly, while one that arrived in a solution points at a connectionreference row - and activate: true turns the flow on in the same call. cs_set_flow_state turns one on by itself once it is bound.

Work out why a run failed. The run list says a run failed and nothing more.

A trigger that failed means the flow never ran at all, so the fault is in the trigger's connection or its parameters rather than the logic. Run detail ages out: inputs and outputs are kept for a limited time, so diagnose a failure while it is recent.

Two things the builder cannot do for you. The connections themselves must exist in the target environment before anything can be bound to them, which is why a new flow is created switched off. And the definitions follow the Logic Apps schema and exported solutions rather than a verified round trip, so import one and open it in Power Automate before trusting the shape.

Ship a solution to another environment

Per-agent sync stays bound to the environment the agent came from. Moving to test or production is a solution export and import, and the server makes that a pull, a settings file and a deploy.

1. See what you are moving. cs_list_solutions, then cs_describe_solution exports, unpacks and inventories: agents, bot components, flows, connection references, environment variables, custom connectors.
2. Pull it. cs_pull_solution exports the solution unmanaged and managed, unpacks it to src/, writes solution.json (the manifest the deploy reads), creates deployment-settings.json and clones every agent into agents/. A full pull runs for minutes, so pass background: true and follow it with cs_job_status; the outcome also lands in pull-job.json in the target directory.
3. Map the target. cs_list_connections on the target environment shows the connections that exist there; cs_create_deployment_settings maps each connection reference to one of them, sets the environment variable values for the target and, per agent, the Entra security group that may use it.
4. Deploy. cs_deploy_solution confirm=true imports into the target with the settings file and runs pac copilot publish on every agent (publishAgents, default on). It refuses to import while any connection reference is unmapped unless you pass allowUnmapped: true. If you edited src/ by hand, cs_pack_solution first.

Quality gates and alternatives on the same path: cs_check_solution runs Solution Checker before a deploy; cs_set_solution_version, cs_solution_online_version and cs_upgrade_solution handle release numbering and staged upgrades; cs_publish_customizations publishes everything in an environment; cs_list_pipelines and cs_deploy_pipeline use Power Platform pipelines instead of a direct import; cs_init_solution_project, cs_clone_solution, cs_sync_solution, cs_add_solution_reference and cs_add_solution_license keep a source-controlled solution project (.cdsproj); cs_add_solution_component adds an existing component to a solution.

What no tooling carries across

Plan for these before calling the copy "1:1":

Documentation truncated — see the full README on GitHub.