EyalSec MCP Server

Official

by EyalSec

Overview Schema Source Related Servers Discussions Admin

Python

Remote

Events map

event_map

Read-onlyIdempotent

Trace untrusted data from its source to the sink it reached, showing files, hit counts, and worst severity as a graph. Filter by date window, severity, or tags.

Instructions

The es-python events as a graph: which sources untrusted data came from, which files it was read from, and which operations (sinks) it reached, each with event and hit counts and the worst severity. Prefer a date window on a large account.

Input Schema

TableJSON Schema

Name	Required	Description
`tags`	No	Impact classes to keep, such as 'xss' or 'sqli'.
`bucket`	No	'live' (default: events not suppressed), 'suppressed', or 'all'.
`labels`	No	Label ids (from list_labels) to keep.
`date_to`	No	End date, YYYY-MM-DD or RFC3339; includes that whole day.
`machine`	No	One machine, by its display name (exact match).
`run_uid`	No	Only events produced by this run (a run_uid from list_runs or get_event). es-python only.
`sources`	No	Keep only these taint source categories.
`advanced`	No	The events page condition builder, passed through as is: {"match": "all"\|"any", "conditions": [{"field": "sink", "op": "contains", "value": "sql", "negate": false}]}.
`severity`	No	Keep only these severities.
`date_from`	No	Start date, YYYY-MM-DD or RFC3339.
`focus_file`	No	Focus on one file path, exactly as listed in 'files'.
`focus_sink`	No	Focus on one sink, exactly as listed in 'sinks'.
`focus_source`	No	Focus on one source category (or 'other') and list its newest events.
`sink_exclude`	No	Case-insensitive regex; drop events whose sink label ('where') matches.
`sink_include`	No	Case-insensitive regex; keep only events whose sink label ('where') matches.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 15, 2026

TDQS

B3.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's main added value is the shape of the graph it returns and the scale warning. It does not disclose scoping limits (e.g. es-python-only behavior, which the schema notes for run_uid) or any cost/latency characteristics beyond the date-window hint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the graph concept and closed with an actionable performance note; no filler. It could be tightened slightly but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter tool with an output schema and full annotations, the description covers the conceptual model and the key scale caveat, which is enough for an agent to call it correctly. Missing is routing guidance against the numerous sibling event tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all 15 parameters are already documented in the schema; the description merely gestures at the source/file/sink/severity concepts those parameters filter on without adding syntax or edge-case meaning. This is the expected baseline when the schema carries the burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource relationship: it renders es-python taint events as a graph of sources → files → sinks, and describes the per-node payload (event/hit counts, worst severity). That is far more specific than siblings like event_stats or event_counts, though it never names a sibling to differentiate itself directly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only guidance is 'Prefer a date window on a large account', which is a performance tip about a parameter rather than a statement of when this tool should be chosen over search_events, event_stats, or event_counts. No when-not conditions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.