New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice
// MCP SERVER RECORD

A11y Agent

Unverified
NPM@a11y-agent/mcp
DRisk gradehigh blast radius
Catalogue entry updated 37 days ago
Auth postureNot probedno remote endpoint probed yet
Tools63 Execute · 3 Read
Worst categoryExecutegrade tracks the peak, not the average
Capability mix
Execute 3Read 3
What it can reach
Ingests untrusted inputTouches secretsReaches networkRuns codeTouches filesChanges permissionsSends external commsPersistsDeletes dataMoves money
Exfiltration pathReads content an attacker can plant and can send data outward — a prompt-injection-to-exfiltration route.
Tools 6
run_keyboard_journeyExecuteMediumscan_pageExecuteMediumverify_repairExecuteMediumcompare_reportsReadLowget_rule_helpReadLow
View all 6 tools
scan_htmlReadLow
These definitions cost 5,635 tokens of context →
Change history
No change history on record for this server.
Recommended policy
run_keyboard_journeyrequire approval
Read-only toolsallow
Full policy breakdown with enforcement rules →

This record as markdown: /tools/a11y-agent-mcp.md — append .md to any tool or server page.

// RUNNING THIS SERVER
DIRECT INSTALL npx -y @a11y-agent/mcp

Installed this way, nothing enforces the recommended policy above — calls run exactly as the agent makes them.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.