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

A11y Assist

Unverified
NPMa11y-assist-mcp
DRisk gradehigh blast radius
Catalogue entry updated 9 days ago
Auth postureNot probedno remote endpoint probed yet
Tools122 Execute · 1 Write · 9 Read
Worst categoryExecutegrade tracks the peak, not the average
Capability mix
Execute 2Write 1Read 9
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 12
audit_htmlExecuteMediumaudit_urlExecuteMediumevaluate_applicabilityWriteMediumevaluate_verificationReadLowget_act_ruleReadLow
View all 12 tools
get_apg_patternReadLowget_aria_roleReadLowget_element_rolesReadLowget_wcag_scReadLowlist_apg_patternsReadLowsearch_actReadLowsearch_wcagReadLow
These definitions cost 2,569 tokens of context →
Change history
No change history on record for this server.
Recommended policy
audit_htmlrequire approval
evaluate_applicabilityrate limit
Read-only toolsallow
Full policy breakdown with enforcement rules →

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

// RUNNING THIS SERVER
DIRECT INSTALL npx -y a11y-assist-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.