For Teams

People and agents. One admin console.

Your team members and your AI agents need the same things — the right tools, the right scope, the right oversight. MCP Link Layer puts both under one identity system, one tool-assignment workflow, one live operations feed, one audit trail. Run a company, not two parallel systems.

Free during beta. No credit card required.

Built for teams where people and agents work side by side

Unified Admin Console

Teammates and AI agents are both first-class principals. One invite flow, one tool-assignment surface, one decommission button — whether you're onboarding a new engineer or spinning up a new agent. No two parallel admin stacks to keep in sync.

Live Operations View

Watch every tool call from every principal as it happens — the junior dev's Jira ticket update next to the nightly agent's database sync. Same feed, same filters, same detail view. No more 'where did that action come from?'

Per-Principal Access Profiles

The same access-profile model scopes tools for a person or an agent: read-only DB for the reporting agent, full access for the backend lead, Slack but not Jira for the intern. Rate-limit per principal. Enforce at the gateway.

Approval & Block Gates

Route high-risk calls to a human reviewer before they run — triggered by the action, not by who's calling it. Auto-block destructive patterns at the firewall. Every decision, human or agent, lands in the same audit trail.

Live preview

Your operations, live.

A live, animated preview — people and agents, tool calls streaming in, approvals queued, blocks enforced. Everything pure code, no screenshots, always in sync with the real product.

app.tryweave.de/operations
LIVE
Tool calls / hour12,847
Active principals5 / 6
Awaiting approval2

Principals

6
  • SC
    Sarah Chen
    Engineering Lead
  • AH
    Ahmed Hassan
    Backend Dev
  • MR
    Mira Rossi
    Data Analyst
  • reporting-agent
    v2.1 · scheduled
  • deploy-agent
    on-demand
  • support-bot
    always-on

Live tool calls

auto-scroll on
  • ··:··:··sarahgithub.create_prrepo: bina165/api · feat: agent approval queue312msOK
  • ··:··:··reporting-agentpostgres.querySELECT count(*) FROM signups WHERE created_at > now() - '24h'142msOK
  • ··:··:··support-botslack.post_messagechannel: #customer-support · incident update89msREVIEW
  • ··:··:··ahmedsentry.get_error_countproject: api-prod · last 1h203msOK
  • ··:··:··deploy-agentgithub.merge_prpr: #4812 · main ← staging456msOK
  • ··:··:··miraweave.audit_searchfilter: principal=support-bot · verdict=blocked78msOK

Approval queue

2
support-bot
slack.post_message
NEW
Post to #customer-support
Our billing system had a 14-minute outage tonight between 02:17 – 02:31 UTC. No charges were affected. Full post-mortem tomorrow.
1 more pending
Mockup · not connected to your data · every animation is pure code

One workflow for every user and every agent in your team

1

Add people and agents

Invite teammates and declare each AI agent as its own named principal through the same onboarding flow. No shared keys, no anonymous calls, no shadow accounts.

2

Assign tools & guardrails to both

Drop tools into access profiles and attach them to people or agents — the same profile works for a human analyst or an automated agent. Wire approval flows and rate limits where you want a safety net.

3

Monitor both in real time

One live operations feed, one audit trail, one place to review blocked calls and approve queued actions. No context-switching between a user dashboard and an agent dashboard.

Run a fleet

One team. Many specialised agents.

Your team members use the platform directly. Alongside them you can operate a whole fleet of AI agents — each one with its own tool stack and its own credentials, administered independently but audited as a whole.

Research
Research Agent
arXiv · Notion · Web Search
Read-only scopes. Shared with the comms team.
DevOps
DevOps Agent
GitHub · PagerDuty · Datadog
Dedicated container. Confirm-to-deploy gate.
Support
Support Agent
Zendesk · Slack · Intercom
Scoped to one product. No write outside tickets.
Data
Analytics Agent
BigQuery · Looker · Snowflake
Read-only roles. Queries audited row-by-row.

Same backend. Same firewall. Same audit. Each agent independently provisioned, revoked, rotated — without touching any of the others or your team members' own toolboxes.

The admin + monitoring surface

Unified Operations Console

Live feed of every tool call from every principal — human or agent — with duration, result, and firewall verdict. Plus adoption, spend, and system health in one view.

Shared Access Profiles

Define a scope once, reuse it for any principal. Bulk-reassign across teammates and agents. Change policy for twenty principals in one action — works the same whether they're human or agent.

Named Principals for Both

One identity system for teammates and AI agents. Each principal has its own key, scope, and audit line. Decommission a principal — person or agent — and its access disappears everywhere, instantly.

GDPR Compliant
Per-Tenant Encryption
Hosted in Germany
Role-Based Access
MCP Firewall
Full Audit Trail

Ready to run your people AND your AI agents on one console?

Start a team workspace and bring every human teammate and every agent under one admin and monitoring surface in minutes.

Need enterprise governance? See Enterprise features