Parseable MCP server

Read from the package source without running it. The installed server may list more.

• create_alertwrite action

  Create a new Parseable alert. BEFORE calling this tool, gather inputs from the user ONE QUESTION AT A TIME. Do not invent values. Ask in this order: 1. "What should this alert be called?" → title 2. "Which dataset should it watch?" → call list_datasets if user is unsure, then pick 3. "What condition should trigger it?" → translate user's natural-language condition into: - alert SQL against the sel

• create_alert_targetwrite action

  Create a new notification target (Slack/webhook/Alertmanager). Ask the user step-by-step: name, type, endpoint URL, then type-specific fields (headers for webhook, basic auth for Alertmanager). Confirm full JSON before submitting.

• disable_alert

  Disable an active alert (stops evaluating + firing).

• enable_alert

  Enable a previously-disabled alert.

• evaluate_alert

  Force-evaluate an alert immediately (out-of-schedule). MAY TRIGGER REAL NOTIFICATIONS if threshold breached - confirm with user before running on production alerts.

• explain_querywrite action

  Run EXPLAIN on a SQL query to see the DataFusion execution plan without executing it. Useful for debugging slow queries, verifying predicate pushdown, and checking partition pruning. Same SELECT-only restriction as query_sql.

• get_alert

  Get full configuration for one alert: query, threshold, evaluation window, targets, tags, state, last fired timestamp.

• get_alert_target

  Get full config for one alert target (endpoint URL, auth, headers, notification interval).

• get_cluster_metrics

  Get aggregated metrics across all nodes in this Parseable cluster (ingest rate, query latency, storage utilization, errors). Distributed mode only.

• get_cluster_status

  List all nodes in this Parseable cluster (Prism, Querier, Ingestor, Indexer) with their domains, status, and metadata. Only works on distributed Parseable deployments - standalone instances will return an error.

• get_dataset_info

  Get metadata for a dataset: created_at, first/last event time, owner, retention, hot-tier config, time partition.

• get_dataset_schema

  Get the Arrow schema (columns + types) for a dataset. Run this before writing SQL so you know available columns.

• get_dataset_stats

  Get event count, ingested bytes, and storage (compressed) bytes for a dataset. Useful for cost and volume audits.

• get_default_role

  Get the default role assigned to new users on this Parseable server. Returns the role name, or null if no default is set.

• get_retention

  Get the retention policy for a dataset - how long data is kept before being deleted, and any tiering rules. Read-only; modification stays in the Parseable UI.

• get_role

  Get the full privilege definition for a role: which actions (Ingest, Query, GetStream, PutAlert, etc.) the role grants, and which datasets each privilege applies to. Use to answer 'does role X let me write to dataset Y?' style questions.

• get_user_roles

  Get the roles assigned to a specific user. Returns a map of role name → role definition. Combine with list_roles + get_role to determine effective permissions for a user (which datasets they can read, write, manage alerts on, etc.).

• list_alert_tags

  List all tags currently in use across alerts. Useful for filtering and grouping alerts by service/team/severity.

• list_alert_targets

  List all alert notification targets (Slack webhooks, generic webhooks, Alertmanager endpoints) configured on this Parseable server. Returns array of `{id, name, type, ...}`. Use BEFORE create_alert so the user can pick valid target IDs for the alert's `targets` array.

• list_alerts

  List all alerts on this Parseable server with their IDs, names, state (enabled/disabled), severity, and last evaluation. Use first to discover what alerts exist before drilling in with get_alert.

• list_datasets

  List all log datasets (streams) on this Parseable server. Returns an array of dataset metadata. Use this first to discover what data is available.

• list_roles

  List all roles defined on this Parseable server. Returns role names. Use get_role on each to inspect privileges. Read-only - this server does not provide role creation/modification.

• list_users

  List all registered users on this Parseable server. Returns user IDs and basic metadata. Caller must have ListUser permission. Read-only - this server does not provide user creation/deletion.

• ping

  Check connectivity and report server version/build info. Returns about (version, mode, license, deployment id), liveness, and readiness. Use for diagnosing MCP-server-to-Parseable connection issues.

• query_promqlwrite action

  Execute a PromQL query against a Parseable metrics dataset. Pass start+end+step for a range query (time series), or omit them for an instant query (single point). Requires a metrics dataset name in `stream`.

• query_sqlwrite action

  Execute a SQL SELECT against a Parseable dataset over a time window. Use this for any analytical question on logs/events. Run get_dataset_schema first to know columns. Time window is mandatory.

• sample_events

  Return the most recent N events from a dataset. Useful for understanding the shape of data before writing SQL.

• Code scan79 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 33 days ago12/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10

Safety score

89/100

higher than 83% of 4,460 AI and agents servers

Tools

27

the typical AI and agents server has 6

Tools that change things

19%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

4

more than 77% of 2,711 AI and agents servers

Downloads a week

45

more than 37% of 1,538 AI and agents servers with a package

Parseable: common questions

Is Parseable MCP server safe?

Yes, by our scan: it is graded A (89/100). Read the Parseable safety report

How do I install Parseable?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Parseable need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Parseable maintained?

The last commit was 74 days ago (2026-08-22). The latest release is v0.2.16.

What can I use instead of Parseable?

Servers from other publishers that do the same job: three.ws Marketplace MCP server.

How does Parseable compare with other AI and agents MCP servers?

safety score 89/100 (higher than 83% of 4,460 AI and agents servers); tools 27 (the typical AI and agents server has 6); tools that change things 19% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.