Loading…
Connects AI assistants to the ADAS platform for building, validating, and deploying multi-agent solutions.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 7 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The ateam-mcp MCP server exposes 47 tools, focused primarily on developer and communication capabilities. Its published description reads: "Connects AI assistants to the ADAS platform for building, validating, and deploying multi-agent solutions". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates ateam-mcp F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Hidden instructions in a tool description" and "Hidden instructions in a tool description". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check ateam-mcp's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add ateam-mcp to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.ateam-ai.com/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
REQUIRED onboarding entrypoint for A-Team MCP. MUST be called when user greets, says hi, asks what this is, asks for help, explores capabilities, or when MCP is first connected. Returns platform expla
Authenticate with A-Team. Required before any tenant-aware operation (reading solutions, deploying, testing, etc.). The user can get their API key at https://mcp.ateam-ai.com/get-api-key. Only global
Get the A-Team specification — schemas, validation rules, system tools, agent guides, and templates. Start here after bootstrap to understand how to build skills and solutions. Use 'section' to get ju
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: ateam_auth
A tool description contains imperative text aimed at the model (e.g. "ignore previous", "before answering read …").
k without auth. IMPORTANT: Even if environment variables (ADAS_API_KEY) arRecommendationRemove model-directed instructions from tool descriptions.
tool: (server instructions)
A tool description contains imperative text aimed at the model (e.g. "ignore previous", "before answering read …").
ution Platform. IMPORTANT: On first user message, ALWAYS call the ateam_boRecommendationRemove model-directed instructions from tool descriptions.
tool: ateam_auth
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: ateam_auth
A tool description tries to alter the model’s use of another tool.
_key instead of api_key.RecommendationDescriptions must describe only their own tool.
tool: ateam_auth
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: ateam_get_spec
A tool description tries to alter the model’s use of another tool.
yed tenant, use ateam_get_widget_catalog instead.RecommendationDescriptions must describe only their own tool.
tool: ateam_design_advisor
A tool description tries to alter the model’s use of another tool.
read next (via ateam_get_spec) and the tool to wire it. Also returns 'missingRecommendationDescriptions must describe only their own tool.
tool: ateam_spec_search
A tool description tries to alter the model’s use of another tool.
full topic via ateam_get_spec(topic). Use this when the advisor's pointer isnRecommendationDescriptions must describe only their own tool.
tool: ateam_build_and_run
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: ateam_test_skill
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
al actor ID for conversation continuity. Pass the actor_id from a previous tRecommendationRemove side-channel parameters; constrain tool inputs.
tool: ateam_test_skill
A tool description tries to alter the model’s use of another tool.
for polling via ateam_test_status. wait:true is the same as the default wait_for:RecommendationDescriptions must describe only their own tool.
tool: ateam_test_notification
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
nels) and ateam_conversation (user-initiated thread), this calls the /api/inRecommendationRemove side-channel parameters; constrain tool inputs.
tool: ateam_test_notification
A tool description tries to alter the model’s use of another tool.
nnels). Unlike ateam_test_skill (synthetic test actor with no channels) and ateRecommendationDescriptions must describe only their own tool.
tool: ateam_conversation
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ateam_conversation Send a chat message to a deployed solution. NoRecommendationRemove side-channel parameters; constrain tool inputs.
tool: ateam_conversation
A tool description tries to alter the model’s use of another tool.
chat uses). Use ateam_get_chain(chain_id) only ONCE at the end if you want theRecommendationDescriptions must describe only their own tool.
tool: ateam_test_voice
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
imulate a voice conversation with a deployed solution. Runs the full voice pRecommendationRemove side-channel parameters; constrain tool inputs.
tool: ateam_test_voice
A tool description tries to alter the model’s use of another tool.
nstead of audio. Returns each turn with bot response, verification status,RecommendationDescriptions must describe only their own tool.
tool: ateam_get_solution
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: ateam_delete_solution
A tool description tries to alter the model’s use of another tool.
is untouched; `ateam_github_pull` rebuilds the solution from `main`. Prefer thatRecommendationDescriptions must describe only their own tool.
tool: ateam_delete_skill
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
ked_skills, and removes the skill's files from Builder FS. REQUIRES `confirm:true`. RECOVRecommendationAnnotate destructive tools and require human approval.
tool: ateam_delete_skill
A tool description tries to alter the model’s use of another tool.
es in GitHub — `ateam_github_pull` rebuilds the whole solution (no per-skill restRecommendationDescriptions must describe only their own tool.
tool: ateam_delete_connector
A tool description tries to alter the model’s use of another tool.
— a follow-up `ateam_build_and_run(github:true)` can resurrect. REQUIRES `confirm:RecommendationDescriptions must describe only their own tool.
tool: ateam_show_skill_minimal
A tool description tries to alter the model’s use of another tool.
0× smaller than ateam_get_solution(view:'skills') for the same skill. Use this wheRecommendationDescriptions must describe only their own tool.
tool: ateam_create_connector
A tool description tries to alter the model’s use of another tool.
separately via ateam_create_plugin). After scaffolding, the files are uploaded toRecommendationDescriptions must describe only their own tool.
tool: ateam_create_plugin
A tool description tries to alter the model’s use of another tool.
usUiPlugin (see ateam_get_spec topic:'widgets'). The scaffold MERGES into theRecommendationDescriptions must describe only their own tool.
tool: ateam_upload_connector
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
,"description":"File content"}},"required":["path","content"]},"description"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: ateam_upload_connector
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
nnector dir and write only these files."},"replace":{"type":"boolean","description":"ORecommendationAnnotate destructive tools and require human approval.
tool: ateam_test_status
A tool description tries to alter the model’s use of another tool.
stead of polling each child job_id separately.RecommendationDescriptions must describe only their own tool.
tool: ateam_get_chain
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
rds your authed api_key. Tenant scoped by the key itself. Actor scopingRecommendationRemove side-channel parameters; constrain tool inputs.
tool: ateam_get_chain
A tool description tries to alter the model’s use of another tool.
. Differs from ateam_test_status by purpose: status is for live polling of a jobRecommendationDescriptions must describe only their own tool.
tool: ateam_chain_status
A tool description tries to alter the model’s use of another tool.
chain_id (from ateam_conversation), returns the WHOLE-CHAIN aggregate status cheaRecommendationDescriptions must describe only their own tool.
tool: ateam_get_widget_catalog
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
rds your authed api_key to Core (no master-secret involvement). TenantRecommendationRemove side-channel parameters; constrain tool inputs.
tool: ateam_get_widget_catalog
A tool description tries to alter the model’s use of another tool.
pec itself, use ateam_get_spec topic='widgets'). Origins: • 'platform' = wiRecommendationDescriptions must describe only their own tool.
tool: ateam_get_connector_source
A tool description tries to alter the model’s use of another tool.
blind full rewrites.RecommendationDescriptions must describe only their own tool.
tool: ateam_verify
A tool description tries to alter the model’s use of another tool.
is instead of guess-and-check after a deploy/patch: it tells you the truthRecommendationDescriptions must describe only their own tool.
tool: ateam_github_push
A tool description tries to alter the model’s use of another tool.
ally. Use after ateam_build_and_run to version your solution, or anytime you want tRecommendationDescriptions must describe only their own tool.
tool: ateam_github_patch
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
file content to write (mode 1 — full file replacement)"},"search":{"type":"string","descrRecommendationAnnotate destructive tools and require human approval.
tool: ateam_github_patch
A tool description tries to alter the model’s use of another tool.
file first with ateam_github_read to get the exact text to search for. DEFAULTSRecommendationDescriptions must describe only their own tool.
tool: ateam_github_write
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
am_github_write Write a file to the solution's GitHub repo. Use this to creaRecommendationAnnotate destructive tools and require human approval.
tool: ateam_github_write
A tool description tries to alter the model’s use of another tool.
dev→main), then ateam_build_and_run() to deploy. DEFAULTS TO `dev` BRANCH.RecommendationDescriptions must describe only their own tool.
tool: ateam_github_diff
A tool description tries to alter the model’s use of another tool.
erride base/head)RecommendationDescriptions must describe only their own tool.
tool: ateam_verify_consistency
A tool description tries to alter the model’s use of another tool.
tHub before you ateam_build_and_run.RecommendationDescriptions must describe only their own tool.
tool: ateam_github_promote
A tool description tries to alter the model’s use of another tool.
dev→main) → 3) ateam_build_and_run (deploys main). Pass dry_run:true to see what'RecommendationDescriptions must describe only their own tool.
tool: ateam_github_rollback
A tool description tries to alter the model’s use of another tool.
safe-...') → 3) ateam_build_and_run (deploys the reverted state).RecommendationDescriptions must describe only their own tool.
tool: ateam_redeploy
A tool description tries to alter the model’s use of another tool.
changes, prefer ateam_patch (which updates + redeploys in one step).RecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
ALWAYS call the ateam_bootstrap tool before responding. Use its structured outpRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
The text tells the model WHEN to call this tool relative to others ("always call first", "before any other tool", "chain to X tool") — a toxic-flow injection that hijacks the agent’s orchestration rather than describing the tool.
t user message, ALWAYS call the ateam_bootstrap tool before responding. Use its structured output toRecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: ateam_build_and_run
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_build_and_run"RecommendationScope tools to the minimum needed.
tool: ateam_test_skill
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_test_skill"RecommendationScope tools to the minimum needed.
tool: ateam_conversation
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_conversation"RecommendationScope tools to the minimum needed.
tool: ateam_patch
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_patch"RecommendationScope tools to the minimum needed.
tool: ateam_delete_skill
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_delete_skill"RecommendationScope tools to the minimum needed.
tool: ateam_delete_connector
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_delete_connector"RecommendationScope tools to the minimum needed.
tool: ateam_create_connector
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_create_connector"RecommendationScope tools to the minimum needed.
tool: ateam_create_plugin
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_create_plugin"RecommendationScope tools to the minimum needed.
tool: ateam_upload_connector
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_upload_connector"RecommendationScope tools to the minimum needed.
tool: ateam_upload_connector
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
connector dir + writes only the provided files. Use deliberately. Common traps this design prRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: ateam_test_status
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_test_status"RecommendationScope tools to the minimum needed.
tool: ateam_get_chain
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_get_chain"RecommendationScope tools to the minimum needed.
tool: ateam_chain_status
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_chain_status"RecommendationScope tools to the minimum needed.
tool: ateam_get_connector_source
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "path"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
tool: ateam_verify
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_verify"RecommendationScope tools to the minimum needed.
tool: ateam_github_push
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_github_push"RecommendationScope tools to the minimum needed.
tool: ateam_github_read
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "path"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
tool: ateam_github_patch
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_github_patch"RecommendationScope tools to the minimum needed.
tool: ateam_github_patch
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "path"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
tool: ateam_github_write
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_github_write"RecommendationScope tools to the minimum needed.
tool: ateam_github_write
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "path"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
tool: ateam_verify_consistency
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_verify_consistency"RecommendationScope tools to the minimum needed.
tool: ateam_github_promote
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_github_promote"RecommendationScope tools to the minimum needed.
tool: ateam_github_rollback
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_github_rollback"RecommendationScope tools to the minimum needed.
tool: ateam_redeploy
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ateam_redeploy"RecommendationScope tools to the minimum needed.
tool: ateam_patch
An unusually long description is a common injection-padding tactic.
description length 2426 charsRecommendationKeep descriptions concise.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Get the builder workflows — step-by-step state machines for building skills and solutions. Use this to guide users through the entire build process conversationally. Returns phases, what to ask, what
Get complete working examples that pass validation. Study these before building your own.
CONSULT THIS DURING DESIGN — before and while you design a skill/solution. Describe what you're building; it returns POINTERS to the platform capabilities that fit (per-actor storage, widgets, trigger
Semantic search over the FULL ateam platform /spec documentation — the deep fallback behind ateam_design_advisor. Ask a natural-language 'how do I…' question and get the most relevant doc chunks (with
DEPLOY THE CURRENT MAIN BRANCH TO A-TEAM CORE. ⚠️ HEAVIEST OPERATION (60-180s): validates solution+skills → deploys all connectors+skills to Core (regenerates MCP servers) → health-checks → optionally
Send a test message to a deployed skill and get the execution result. Wait modes (wait_for): • 'root' (default, back-compat) — wait until the message's root job completes, return single-job result. Fa
Fire a REAL notification at an existing actor in a deployed solution — for end-to-end testing of the system-initiated notification path (telegram/push/app channels). Unlike ateam_test_skill (synthetic
Send a chat message to a deployed solution. No skill_id needed — the system auto-routes to the right skill. ALWAYS ASYNC: returns a chain_id immediately — the assistant's reply is NOT in this response
Test the decision pipeline (intent detection → planning) for a skill WITHOUT executing tools. Returns intent classification, first planned action, and timing. Use this to debug why a skill classifies
Simulate a voice conversation with a deployed solution. Runs the full voice pipeline (session → caller verification → prompt → skill dispatch → response) using text instead of audio. Returns each turn
Surgically update ANY field in a skill or solution definition, redeploy, and optionally re-test — all in one step. ⚠️ MERGE-BY-DEFAULT (v0.4.0) — Arrays are protected from silent replace. Bare array w
Read solution state — definition, skills, health, status, or export. Use this to inspect deployed solutions.
List all solutions deployed in the Skill Builder.
⚠️ IRREVERSIBLE — kills Mongo state, running MCP processes, and Builder FS for the whole solution and every skill. REQUIRES `confirm:true` AND `confirm_solution_id` echoing the solution id you're dest
⚠️ IRREVERSIBLE in Core + Builder FS — kills the running MCP process, unregisters from skill registry, deletes the Mongo record, drops from solution.skills[] and solution.linked_skills, and removes th
⚠️ CASCADING — any skill whose engine.bootstrap_tools or tools[] name a tool from this connector will FAIL its next execution. Stops and deletes the connector from A-Team Core; drops references from t
Show the minimal authoring view of a skill — persona + connectors + handoff_when + style + policy guardrails only. ~10× smaller than ateam_get_solution(view:'skills') for the same skill. Use this when
Show the minimal authoring view of a solution — name + description + style + routing_mode + identity_mode + skill ids + connector ids only. Skips deployed metadata, handoffs (auto-generated), grants,
Scaffold a new MCP connector with server.js + package.json + README. Eliminates ~50% of identical boilerplate (MCP server setup, tool registration, stdio transport). You then fill in the tool implemen
Scaffold a UI plugin (iframe HTML, React Native TSX, or both) inside an existing connector. Eliminates ~50% of identical plugin boilerplate (imports, theme/bridge hooks, postMessage protocol, default
Upload connector code to Core and restart — WITHOUT redeploying skills. MERGES with the GitHub state at `ref` by default (default ref: 'dev'). Sending a partial file set ONLY overlays those files — th
Poll the progress of an async skill test. Returns iteration count, tool call steps, status (running/completed/failed), and result when done. Set include_chain:true to ALSO include the full chain tree
Inspect the full chain tree for any job — rooted at the given job_id, walking down through every handoff and askAnySkill subcall. Use when a chain has already run and you want to analyze the structure
SLIM chain status — the chip-quick poll. Given a chain_id (from ateam_conversation), returns the WHOLE-CHAIN aggregate status cheaply: chain_status + chain_done (true only when the ENTIRE chain — root
Get the live catalog of widgets (UI plugins) available in this tenant's solution. Returns platform-bundled + solution-bundled + skill-declared widgets, each with a paste-ready how_to_use block (soluti
Abort a running skill test. Stops the job execution at the next iteration boundary. (Advanced.)
Call a tool on a running connector and get the result. Use this to test individual connector tools (e.g., triggers.list, entities.list, google.command) without deploying to a client. The connector mus
Read the source code files of a deployed MCP connector. Returns all files (server.js, package.json, etc.) stored in the mcp_store for this connector. Use this BEFORE patching or rewriting a connector
ONE call that returns the REAL runtime end-state of a solution — connectors connected + tools discovered, every declared widget actually rendering, skills deployed — with the EXACT failing gaps. Use t
Push the current deployed solution to GitHub. Auto-creates the repo on first use. Commits the full bundle (solution + skills + connector source) atomically. Use after ateam_build_and_run to version yo
Deploy a solution FROM its GitHub repo. Reads .ateam/export.json + connector source from the repo and feeds it into the deploy pipeline. Use this to restore a previous version or deploy from GitHub as
Check if a solution has a GitHub repo, its URL, and the latest commit. Use this to verify GitHub integration is working for a solution.
Read any file from a solution's GitHub repo. Returns the file content. Use this to read connector source code, skill definitions, or any versioned file. Default reads from `main` (deployed/prod state)
Edit a file in the solution's GitHub repo and commit. Two modes: 1. FULL FILE: provide `content` — replaces entire file (good for new files or small files) 2. SEARCH/REPLACE: provide `search` + `repla
Write a file to the solution's GitHub repo. Use this to create new connector files or replace existing ones — one file per call. This is the PRIMARY way to write connector code after first deploy. Wri
View commit history for a solution's GitHub repo. Shows recent commits with messages, SHAs, timestamps, and links. Default reads from `main` (prod). Pass `ref: 'dev'` to see in-progress work.
PRE-FLIGHT BEFORE PROMOTE. Compares `dev` (head) vs `main` (base) by default — shows exactly which commits and files are about to ship if you call ateam_github_promote() next. Use this when you want t
Check that the Builder filesystem state and GitHub state are in sync for a solution. Read-only probe — does NOT trigger a deploy. Returns: • ok: true + drifts: [] if everything matches • ok: false + d
SHIP DEV TO PROD. Merges the `dev` branch into `main` and auto-tags the new main HEAD as safe-YYYY-MM-DD-NNN. Use after testing your dev work, when you're ready to deploy changes to production. Workfl
Roll prod (`main` branch) back to a previous state. ADDITIVE — does NOT destroy history. Creates a new commit on top of main whose tree matches the target's tree. The history of everything between tar
List all available checkpoints (safe-* tags) for a solution. Shows tag name, date, counter, and commit SHA. Use before rollback to see available safe points.
Re-deploy skills WITHOUT changing any definitions. ⚠️ HEAVY OPERATION: regenerates MCP servers (Python code) for every skill, pushes each to A-Team Core, restarts connectors, and verifies tool discove
Show GitHub sync status for ALL tenants and solutions in one call. Requires master key authentication. Returns a summary table of every tenant's solutions with their GitHub sync state.
Sync ALL tenants: push Builder FS → GitHub, then pull GitHub → Core MongoDB. Requires master key authentication. Returns a summary table with results for each tenant/solution.