For AI Agents
Hand your agent this brief or the ReUI MCP, not a screenshot. Installs with a ReUI Pro or Ultimate license.
Best for: A table of tool calls by server with status dots, a footnote naming servers that received nothing, and rows that stack in a narrow container
When to use
- A live step feed of one agent run that the person who started it can approve, pause or stop
- The research trail behind an answer: the search query, numbered sources, repo files and confidence
- A record of what a run touched and settled: MCP calls per server, refused scopes and failed items
When not to use
- Setting per tool access modes, rate limits and approvers before any run: use the Tool Access Matrix block
- A step by step narrative of one run naming each file, command and query it touched: use the Live Run Feed block
- Operator pages across many runs: a run queue, an approval inbox or tool access settings: use the Agents blocks
- The conversation around the run: the message thread, the prompt composer and the replies: use the AI Chat blocks
- A dated history of what people did, such as activity feeds, milestones or release notes: use the Timeline blocks
Agent notes
- Replace
SERVERSandCALLS; a call with adeniedScoperanks first and offers Grant, and an emptySERVERSshows the No Servers Connected state grantonly adds the scope to localgrantedstate and firestoast.success; the row turns Re-queued but no call runs again- The
pendingcall stays In flight for good, and the footnote lines on timing and payloads are plain text pointing at views this block lacks - Each page.tsx pads a top aligned
min-h-svhwrapper aroundAgentActivity, whose root caps atmax-w-xlormax-w-2xl; drop the wrapper in your layout - Each run is replayed from the block's data file on
setTimeouttimers; drive the same state from your agent's events instead - Each block calls
toastfromsonnerbut mounts no toaster, so those messages stay hidden until your layout renders one
Third-party API docs
- Sonner v2: API reference, docs
https://web.dev.reui.io/blocks/ai-agents/agent-activity/agent-activity-4.mdget_block("agent-activity-4")npx shadcn@latest add @reui/agent-activity-4Shadcn MCP Call Audit Block
MCP call table attributing each tool call to its server, with the refused scope and a Grant. Part of the ReUI Shadcn AI & Agents Agent Activity blocks collection.
Agent run permission review for a chat transcript: rows stream in over skeletons, a Denied only filter and a Dropped badge on a lost server. Built on ReUI Badge, shadcn Table, ToggleGroup, Empty. For MCP audit log, tool permissions, scope approval.
It is composed from Badge, Button, Empty, Skeleton, Spinner, Table, Toggle Group, so every part of it is a primitive you can restyle with your own design tokens.
What You Can Build With the MCP Call Audit Block
- Install it with the ReUI registry command in the toolbar above, then swap the placeholder content, data wiring, and business logic for your own.
- Compare it across all eight ReUI styles and both the Base UI and Radix bases in the customizer before committing to one direction.
- Combine it with the other Shadcn AI & Agents Agent Activity blocks to assemble a full screen instead of a single section.
All Shadcn AI & Agents Agent Activity Blocks
The rest of this category, each on its own page with a live preview, the components it is built from, and the install command.
- Approval Run Console Agent run console that stops at approval steps for an inline Approve, Revise or Deny
- Live Run Feed Live agent run feed with Summary, Detailed and Raw monospace log views
- Research Timeline Research timeline from search query via cited sources and repo files to a confidence rated answer
- Run Outcome Report Agent run outcome report with a done, failed or skipped badge per item and a scoped retry
Related Shadcn AI & Agents Block Categories
All Shadcn Block Groups
Browse the full ReUI Shadcn blocks library by product surface. Each group bundles category-level blocks you can mix and match across your project.
- Shadcn Application Blocks (303) Browse 303 Shadcn Application blocks across 23 categories.
- Shadcn Data Grid Blocks (47) Browse 47 Shadcn Data Grid blocks across 9 categories.
- Shadcn Charts Blocks (52) Browse 52 Shadcn Charts blocks across 10 categories.
- Shadcn Solutions Blocks (76) Browse 76 Shadcn Solutions blocks across 11 categories.
- Shadcn AI & Agents Blocks (22) Browse 22 Shadcn AI & Agents blocks across 3 categories.
- Shadcn eCommerce Blocks (87) Browse 87 Shadcn eCommerce blocks across 13 categories.
- Shadcn Marketing Blocks (67) Browse 67 Shadcn Marketing blocks across 8 categories.
Frequently Asked Questions
When should I use the MCP Call Audit block?
Use it for a table of tool calls by server with status dots, a footnote naming servers that received nothing, and rows that stack in a narrow container.
The Agent Activity category fits:
- A live step feed of one agent run that the person who started it can approve, pause or stop
- The research trail behind an answer: the search query, numbered sources, repo files and confidence
- A record of what a run touched and settled: MCP calls per server, refused scopes and failed items
For setting per tool access modes, rate limits and approvers before any run, use the Tool Access Matrix block. For a step by step narrative of one run naming each file, command and query it touched, use the Live Run Feed block. For operator pages across many runs: a run queue, an approval inbox or tool access settings, use the Agents blocks. For the conversation around the run: the message thread, the prompt composer and the replies, use the AI Chat blocks. For a dated history of what people did, such as activity feeds, milestones or release notes, use the Timeline blocks.
What is the MCP Call Audit block built with?
Can I restyle the MCP Call Audit block?
How should I use Shadcn agent activity blocks in a real project?
Start building with ReUI Pro today.
Every Pro block, every style, and every future addition, with one license for unlimited projects.
From $249, once. Lifetime updates.