Run-IQ MCP server
Commit Oct 30, 2026Allows AI assistants to write, validate, and evaluate rules and decision graphs using the Run-IQ rule engine.
Also known as Run-IQ/mcp-server
- Stars
- 1
- Tools
- 16
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Oct 30, 2026
- License
- MIT
What is Run-IQ MCP?
Run-IQ allows AI assistants to write, validate, and evaluate rules and decision graphs using the Run-IQ rule engine. It exposes 16 tools, such as create_rule, validate_rules, inspect_rule.
Summary generated from the project's README
About Run-IQ MCP server
Developers using AI clients like Claude Desktop, Cursor, or VS Code can manage complex logic through the Run-IQ rule engine. This server runs locally via stdio and allows an AI assistant to write, validate, and evaluate rules or decision graphs. It functions in a non-strict, dry-run mode where nothing is persisted, making it suitable for testing and prototyping logic without side effects.
To use the server, you must configure it in your client using npx and provide a directory of plugins or specific npm packages. The server starts with no calculation model, so you must load plugins to define specific domains, such as fiscal rules. These plugins provide the necessary schemas and parameters for tools like create_rule and evaluate.
Beyond simple rules, the server includes tools for designing decision graphs. You can build graphs node by node, compile them, and execute them against inputs. It provides specialized tools to inspect graph structures via Mermaid diagrams or to simulate scenarios to see how different inputs affect the outcome.
What you can do with it
- 1Convert regulations into logicTransform a legal text or policy document into a set of functional rules.
- 2Test rule accuracy with simulationsRun a single rule against multiple different inputs to compare the results.
- 3Architect complex decision workflowsDesign a decision graph based on a specific set of requirements.
- 4Verify rule integrityCheck that a rule's structure, checksum, and plugin fields are correct.
Written from the project's README. Every use case is checked against a quote from it.
Run-IQ MCP tools 16
Detected from the READMEcreate_rulevalidate_rulesinspect_rulecreate_checksumlist_modelsevaluatesimulateexplain_resultdesign_graphvalidate_graphcompile_graphinspect_graph
Show all 16 toolsShow fewer tools
execute_graphsimulate_graphinspect_contextexplain_graph_result
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablerun-iq/mcp-server is public and reachablegithub.com/run-iq/mcp-server ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-30github.com/run-iq/mcp-server ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model16 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHub@run-iq/mcp-server
An MCP server that gives LLM clients (Claude Desktop, Claude Code, Cursor, VS Code...) access to the Run-IQ rule engine. The model can write rules, validate them, and evaluate them against test inputs. It runs over stdio.
Install
The package is published to GitHub Packages. Point the @run-iq scope at it in your ~/.npmrc (GitHub requires a token with read:packages):
@run-iq:registry=https://npm.pkg.github.com
//npm.pkg.github.com/:_authToken=YOUR_TOKEN
Then add it to your client's MCP config:
{
"mcpServers": {
"run-iq": {
"command": "npx",
"args": ["-y", "@run-iq/mcp-server", "--plugins-dir", "/path/to/plugins"]
}
}
}
Requires Node.js 20 or later.
Plugins
The server starts with no calculation model. Load plugins with:
| Flag | |
|---|---|
--plugins-dir <dir> |
Imports every .js / .mjs file in the directory |
--plugin <package> |
Imports an npm package, resolved from the current directory, then from ~/.run-iq/mcp-plugins. Missing @run-iq/* packages are installed there automatically |
Both flags can be combined, and --plugin can be repeated. Each module must default-export a PluginBundle from @run-iq/plugin-sdk:
// plugins/fiscal.mjs
import { FiscalPlugin, fiscalDescriptor } from '@run-iq/plugin-fiscal';
import { JsonLogicEvaluator } from '@run-iq/dsl-jsonlogic';
export default {
plugin: new FiscalPlugin(),
descriptor: fiscalDescriptor,
dsls: [new JsonLogicEvaluator()],
};
The packages it imports must be installed next to the file (for example npm install @run-iq/plugin-fiscal @run-iq/dsl-jsonlogic in the parent directory).
The descriptor tells the server which extra fields the plugin's rules need. create_rule, validate_rules, the schema://rules resource and the prompts are built from it. With the fiscal plugin, for example, create_rule requires jurisdiction, scope, country and category.
Tools
| Tool | |
|---|---|
create_rule |
Build a rule and compute its checksum |
validate_rules |
Check structure, checksum, model params and plugin fields |
inspect_rule |
Details on one rule: checksum, model, whether it is active at a date |
create_checksum |
SHA-256 of a rule or of a params object |
list_models |
Models provided by the loaded plugins, with their params |
evaluate |
Evaluate rules against an input |
simulate |
Evaluate the same rules against up to 20 inputs and compare |
explain_result |
Turn an evaluation result into a readable summary |
The engine runs in dry-run, non-strict mode: nothing is persisted and meta.effectiveDate is optional. Rules with a wrong checksum are skipped with CHECKSUM_MISMATCH.
Pass dates to create_rule as full ISO strings (2025-01-01T00:00:00.000Z). With a date-only value like 2025-01-01, the checksum is computed on that string, and evaluate later skips the rule because it normalizes the date first.
Decision graph tools
These tools build and run decision graphs (@run-iq/dg): nodes that compute, fetch data, branch or merge, wired by edges.
| Tool | |
|---|---|
design_graph |
Build a graph one action at a time (add_node, add_edge, remove_node, remove_edge, set_meta, get_current, reset), kept per sessionId |
validate_graph |
Quick structural check without compiling |
compile_graph |
Compile a graph and keep it in memory under its hash |
inspect_graph |
Mermaid diagram, node counts, ports, root and leaf nodes |
execute_graph |
Run a graph, given inline or by hash, against an input |
simulate_graph |
Run the same graph against up to 10 scenarios |
inspect_context |
Per-node outputs and events of a past run, by requestId |
explain_graph_result |
Turn a past run into a readable summary |
Compiled graphs and the last 20 runs live in memory for the session. Compute nodes are evaluated with no rules attached, so they output 0.
Resources and prompts
schema://rules |
Rule schema, plugin fields, model params, input fields and examples |
models://catalog |
Documentation of the available models |
plugins://loaded |
Loaded plugins, DSLs and descriptors |
schema://graph |
Decision graph format: nodes, edges, ports, policies, merge, enrich and subgraph configs |
graph://examples |
Example graphs: linear, merge with enrichment, conditional branching |
analyze-text prompt |
Turn a text (law, regulation, policy) into rules. Args: source_text, optional country |
domain-expert prompt |
Answer a question using the loaded plugins' domain |
orchestration-architect prompt |
Design a decision graph from a requirement, optional country |
License
MIT
Run-IQ MCP questions
What tools does Run-IQ MCP provide?
It exposes 16 tools, including create_rule, validate_rules, inspect_rule, create_checksum, list_models.
Does the engine persist data?
No, the engine runs in a non-strict, dry-run mode where nothing is persisted.
What are the system requirements?
The server requires Node.js version 20 or later.