Skip to main content
Glama

mcp-entity-resolver

Make AI agents stop guessing entity names.

An MCP (Model Context Protocol) server that resolves messy company / customer / vendor names and IDs across CRM, ERP and ITSM systems so your agents act on the right record every time.

The Problem This Solves

AI agents routinely fail in enterprise environments because the same real-world entity appears as:

  • "Acme Corp" in Salesforce

  • "ACME CORPORATION" in SAP

  • "Acme" in ServiceNow

  • "acme-123" in a custom system

Without resolution, the agent updates the wrong record, creates duplicates, or refuses to act. This is one of the top reasons enterprise AI pilots die.

Related MCP server: Regex Toolkit MCP Server

Why This MCP?

  • Computation-heavy, low external cost – pure fuzzy + rule-based matching (Levenshtein + normalization). Optional future embedding backend.

  • Zero or near-zero API spend – works offline after entities are registered.

  • Enterprise-ready tools – resolve, match lists, register confirmed entities, consistency checks.

  • Designed for multi-system agents – Salesforce + SAP + ServiceNow + NetSuite in one conversation.

Tools

Tool

Purpose

resolve_entity

Turn a messy name into the best canonical match + confidence

fuzzy_match_records

Reconcile two lists of records (e.g. SF accounts vs SAP customers)

register_entity

Teach the resolver a confirmed good entity

check_consistency

Detect conflicting attributes for the same logical entity

list_registered_entities

Inspect what the resolver currently knows

Quick Start

# Install
npm install -g mcp-entity-resolver   # or clone + npm i && npm run build

# Run (stdio – works with Claude Desktop, Cursor, etc.)
npx mcp-entity-resolver

Claude Desktop / Cursor config example

{
  "mcpServers": {
    "entity-resolver": {
      "command": "npx",
      "args": ["-y", "mcp-entity-resolver"]
    }
  }
}

Example Agent Conversation

User: "Update the billing address for Acme Corp in SAP"
Agent: (calls resolve_entity with name="Acme Corp")
→ gets canonical id from SAP with high confidence
→ proceeds safely

Pricing Suggestion (for marketplace)

  • Free: up to 500 resolves / day

  • Pro: $49/mo – unlimited + consistency reports

  • Enterprise: $299/mo – private deployment + custom rules + audit log

Roadmap

  • Optional local embedding model (all-MiniLM) for semantic boost

  • Persistent store (SQLite / Postgres)

  • Pre-built connectors that pull live from Salesforce / ServiceNow APIs

  • Human-in-the-loop confirmation queue for low-confidence matches

Author

Prince Ruhul – Founder, Prevalid
GitHub: @princeruhulofficial

Built as part of the Daily AI Project Builder series.

License

MIT

Available Tools

5 tools
check_consistencyA

Check whether the same logical entity has conflicting attributes across systems (e.g. different addresses or status).

Inputs: entity_ids (required).

fuzzy_match_recordsB

Compare two lists of records and return ranked matches. Ideal for reconciling Salesforce accounts vs SAP customers or ServiceNow CIs.

Inputs: source_records (required), target_records (required), threshold.

list_registered_entitiesA

List currently registered entities (useful for debugging agent memory).

Inputs: limit, system.

register_entityA

Register a known good entity into the resolver memory so future lookups can use it. Call this after a human confirms a match.

Inputs: id (required), name (required), system (required), attributes.

resolve_entityA

Resolve a messy entity name or partial record into a canonical match across known systems. Returns best match + confidence. Use this BEFORE any write or action on customer/account/vendor data.

Inputs: name (required), context, threshold, system_hint.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a distinct role: resolving single entities, batch matching, consistency checking, registration, and listing. No two tools overlap in purpose, making selection unambiguous.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case, such as check_consistency, resolve_entity, fuzzy_match_records, register_entity, list_registered_entities. The naming is predictable and uniform.

    Tool Count5/5

    Five tools is well-scoped for an entity resolution server, covering lookup, reconciliation, consistency checks, and memory management without unnecessary bulk.

    Completeness4/5

    The core lifecycle of entity resolution is covered: resolve, reconcile, check consistency, register, and list. The only minor gap is lack of an explicit delete/unregister tool, but this is not essential for the primary workflow.

    Related MCP Connectors

    Related MCP Servers