soar-analyst-mcp
Provides tools for interacting with the Splunk SOAR REST API, enabling SOC analysts to triage cases, retrieve artifacts, notes, action runs, playbook runs and logs, inspect custom lists and assets, and perform allowlisted case updates or response actions.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
soar-analyst-mcp
An MCP server that gives an AI assistant (Claude Code, Claude Desktop, any MCP client) the day-to-day toolkit of a SOC analyst working in Splunk SOAR: triage a case, investigate it, debug a failed playbook run, and, only when you allow it, record findings or launch an allowlisted response.
You: triage case 1001
Claude: get_container(1001) -> "Suspicious PowerShell EncodedCommand", high, edr
get_artifacts(1001) -> host WS-0001, user jdoe, IP 203.0.113.45, sha256 ...
get_action_runs(1001) -> AbuseIPDB score 95, VirusTotal failed (quota)
search_containers(ioc ...) -> same IP seen in case 990 (closed)
=> Verdict: likely True Positive (medium). Hash not enriched (VT quota).
You: re-run the hash lookup and write the summary on the case
Claude: run_action("file reputation", ...) [full mode, allowlisted]
add_note(1001, "AI triage", ...) [standard mode]Safety model
The SOAR role of the automation user is the only boundary that really holds. Anyone with the token can bypass this server with
curl. Everything below is defence in depth.
Modes: SOAR_MCP_MODE
The mode decides which tools are registered. A tool that is not registered does not exist for the model, so the model cannot be talked into calling it.
Mode | Tools | Adds |
| 16 | Every read tool. Cannot change anything. |
| 22 | Notes, comments, case status/severity/sensitivity/owner, artifacts, custom-list rows |
| 24 |
|
Allowlists for execution (full mode)
SOAR_PLAYBOOK_ALLOWLIST: exact playbook namesrun_playbookmay start.SOAR_ACTION_ALLOWLIST: app action namesrun_actionmay start (e.g.ip reputation).
An empty allowlist means nothing can be run, even in full mode. Keep containment playbooks and actions (isolate host, block IP, disable user) out of the allowlists: those stay a human decision in the SOAR UI.
Label scoping: SOAR_ALLOWED_LABELS
When set, every container read and write is limited to those labels. Listings and
searches are filtered. Fetching a case, its artifacts, notes, action runs or playbook runs
outside the set is refused. A refusal reads exactly like "not found" and never names a label,
so the labels cannot be enumerated. server_info reports only how many labels are allowed.
Playbooks, custom lists and assets are instance-wide objects and are not label-scoped.
Credential redaction
SOAR returns asset configuration with credentials in plaintext. Every tool response passes
through one redaction function before it leaves the process. Any field whose name looks like
a secret (password, token, secret, api_key/apiKey, private_key, credential,
authorization, ...) becomes «redacted», at any depth. Matching uses key names, not values,
so hashes and other evidence are never touched. Redaction cannot be turned off.
Other guards
Honest MCP annotations: reads are
readOnlyHint.update_container,run_*and row updates aredestructiveHint, so clients such as Claude Code ask before calling them.No retry on POST: only GETs are retried, so a flaky network cannot run an action twice.
add_artifactalways sendsrun_automation=false: an AI-added artifact never triggers active playbooks.Input validation: status/severity/sensitivity/CEF-field allowlists, label regex, JSON-quoted filter values, size limits on notes, rows, CEF and action parameters. Invalid input is rejected before any request is sent.
Prompt injection: artifact, note, list, log and app-result content is returned with an
UNTRUSTED DATAnotice. The server instructions and prompts tell the model never to act on instructions found inside a case. This reduces the risk but does not remove it. The mode, the allowlists and the SOAR role are what limit the damage.Audit: every call is appended to a JSONL file with time, tool, kind (
read/write/execute), redacted arguments, status, duration and error.
Related MCP server: Splunk MCP for SOC Operations
Tools
Read (all modes)
Tool | Purpose |
| SOAR version, this server's mode, write/execute ability, scoping |
| Cases by status, severity, label, last N hours |
| One case |
| Related cases by name, or by exact IOC value in a CEF field |
| IOCs and evidence (CEF) |
| Analyst notes |
| Actions on a case and their results (enrichment, failures) |
| One action run with its results (poll |
| Playbooks by name, label, active |
| Playbook runs by case, playbook, status |
| One playbook run (poll |
| Debug log of one run, filterable ( |
| Custom lists with row counts |
| Rows of one list (with |
| Integrations: name, vendor, product (no configuration) |
| One asset with configuration, credentials redacted |
Write (standard and full)
Tool | Purpose |
| Status, severity, sensitivity, owner. Returns old → new |
| Titled note, e.g. a triage summary |
| Short activity comment |
| New artifact with CEF fields ( |
| Append one row |
| Replace one row by |
Execute (full only, allowlisted)
Tool | Purpose |
| Start an allowlisted playbook on a case. Returns |
| Run an allowlisted app action against an asset. Returns |
Both are asynchronous. "Started" is not "succeeded": poll get_playbook_run /
get_action_run and read get_playbook_run_log.
Not included on purpose: deleting cases or artifacts, creating cases, user/role management, system settings, raw POST/DELETE.
Resource and prompts
soar://playbooks/catalog: compact list of active playbooks to attach as context.triage_case(container_id): fixed triage report (summary, IOCs, evidence, history, verdict, next steps, ATT&CK).debug_playbook_run(run_id): failing block, root cause, fix, prevention.
Install
Python 3.10+.
git clone https://github.com/yahyayevparviz/soar-analyst-mcp
cd soar-analyst-mcp
pip install -e . # or: uv syncConfigure
All configuration is via environment variables (see .env.example).
Variable | Default | Meaning |
| required | SOAR base URL, e.g. |
| required | Automation user |
|
|
|
|
|
|
| (all) | Comma-separated container labels this server may touch |
| (none) | Playbook names |
| (none) | Action names |
|
| Request timeout, seconds |
|
| Audit log path |
|
| Log level (logs go to stderr) |
Check what a configuration exposes without starting a server:
soar-analyst-mcp --list-tools # current SOAR_MCP_MODE
soar-analyst-mcp --list-tools --mode fullAutomation user role per mode
Create it under Administration → User Management → Users → + User (type Automation) with a role that matches the mode. The SOAR role is what really enforces the limits.
Mode | Suggested SOAR permissions |
| view: containers, playbooks, custom lists, assets, apps |
| + edit: containers, custom lists |
| + execute: playbooks / actions (consider a separate token for this mode) |
Running several modes for different people? Run one process per mode, each with its own automation user, rather than one powerful token behind application checks.
Connect a client
Claude Code
claude mcp add soar-analyst \
-e SOAR_URL=https://soar.example.com \
-e SOAR_TOKEN=your-token \
-e SOAR_MCP_MODE=readonly \
-- soar-analyst-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"soar-analyst": {
"command": "soar-analyst-mcp",
"env": {
"SOAR_URL": "https://soar.example.com",
"SOAR_TOKEN": "your-token",
"SOAR_MCP_MODE": "standard",
"SOAR_ALLOWED_LABELS": "edr,phishing"
}
}
}
}If the command is not on PATH, use the full path to the virtualenv's soar-analyst-mcp.
Without Claude (MCP Inspector): npx @modelcontextprotocol/inspector soar-analyst-mcp
Example prompts
"Show open high-severity cases from the last 24 hours."
"Triage case 1001." (or pick the
triage_caseprompt)"Has 203.0.113.45 appeared in any other case?"
"Why did playbook run 88001 fail?" (or
debug_playbook_run)"Is jdoe on the vip_users list?"
standard: "Write the triage summary as a note on 1001 and set severity to medium."
full: "Run edr_ip_hash_enrichment on case 1001 and tell me when it finishes."
Verify against your SOAR version
Tests run against a fake SOAR. These REST details can vary between SOAR versions, so check them once on your instance (Inspector or curl), ideally on a test label:
Tool | Request | Check |
|
| time filter accepted |
|
| CEF JSON lookup |
|
| app_run filter by container |
|
| log entries returned |
|
| closing may require a resolution on your instance |
|
| row appended |
|
| returns |
|
| returns |
If one differs, the change is local to the matching file in soar_analyst_mcp/tools/.
Development
pip install -e ".[dev]"
pytest -q115 tests, no live SOAR needed:
unit: config, modes, guards, shaping, redaction, client errors
tools: every read, write and execute tool against an in-process fake SOAR, checking the exact payloads sent and that invalid input sends nothing
scoping: reads and writes outside
SOAR_ALLOWED_LABELSrefused, "denied" looks like "missing"server: tool sets and annotations per mode
end-to-end: a real MCP client drives the real server over stdio against a fake SOAR over HTTP, in readonly mode (nothing is POSTed) and in full mode (note, playbook, action)
Layout:
soar_analyst_mcp/
server.py builds the server for the mode, CLI (--list-tools, --mode)
core/
config.py env -> SoarClient
client.py the only HTTP code: GET (retried) and POST (never retried)
modes.py readonly / standard / full, allowlists
scope.py SOAR_ALLOWED_LABELS enforcement
redaction.py credential redaction by key name
guards.py input validation and filter quoting
shaping.py field selection, truncation, untrusted marking
audit.py JSONL audit, central redaction, SoarError -> ToolError
tools/ system, cases, evidence, playbooks, lists, assets, run
resources/catalog.py soar://playbooks/catalog
prompts/templates.py triage_case, debug_playbook_run
descriptions/tools.yaml tool descriptions the model readsAdding a tool: write it in the right tools/ module with @audited("read"|"write"|"execute"),
add its description to descriptions/tools.yaml, and register it in that module's
register_tools under the lowest mode that should have it, with honest annotations. Raise
SoarError for anything the caller can act on: its message reaches the model.
Roadmap
Workbook / phase progress per case
Elicitation-based confirmation for execute tools (on clients that support it)
Streamable HTTP transport with authentication for shared deployments
License
MIT. Not affiliated with or endorsed by Splunk Inc. "Splunk" and "Splunk SOAR" are trademarks of Splunk Inc.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
SOAR security playbooks for AI agents: fetch, full-text search, and count. Metered via Stripe.
Query your app's logs, metrics and incidents from your AI assistant.
Query your AI agent traces, root-cause verdicts and issues, and run investigations, from your agent.
Lets AI agents analyze API metrics, request logs, and traces, and manage apps and alerts.
Related MCP Servers
- AlicenseBqualityAmaintenanceEnables AI agents to interact seamlessly with Splunk environments through 20+ tools for search, analytics, data discovery, administration, and health monitoring. Features AI-powered troubleshooting workflows and supports multiple Splunk instances with production-ready security.57113 PyPI27Apache 2.0
- AlicenseBqualityDmaintenanceEnables AI-driven SOC investigations by providing automated Splunk querying, threat intelligence enrichment, and response actions through natural language. Includes tools for IP pivoting, lateral movement detection, and label harvesting.311Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to search, manage, and analyze data in Splunk instances through the Model Context Protocol. Supports SPL queries, index management, alerts, dashboards, and more.1,663 PyPI1Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to operate a Splunk SOAR instance headlessly via its REST API, supporting container triage, playbook authoring and execution, and asset management.2MIT