Gleif

Search Lei

search_lei

Read-onlyIdempotent

Search the GLEIF LEI registry by legal entity name. Returns matched entities with their 20-character LEI, jurisdiction, status, and BIC/ISIN cross-references. Use the LEI to resolve canonical identity across SEC, OpenSanctions, and counterparty databases. Name matching is whole-token AND against the REGISTERED legal name, so abbreviations that do not literally appear ("Microsoft Corp", "Toyota Motor Corp") match nothing on their own; this tool automatically retries with legal-form suffixes dropped, with the words joined ("Exxon Mobil" -> "ExxonMobil"), and finally against GLEIF fuzzy autocomplete. The response always reports match_mode and searched_as so you can see which query actually produced the rows.

Input Schema

Name	Required	Description
`query`	Yes	Legal entity name (full or partial), e.g. "Apple Inc." or "Siemens Aktiengesellschaft"
`status`	No	Entity status (ACTIVE \| INACTIVE \| NULL) or LEI registration status (ISSUED \| LAPSED \| ANNULLED \| PENDING_TRANSFER \| PENDING_ARCHIVAL \| DUPLICATE \| RETIRED \| MERGED). GLEIF keeps these in two different fields; the tool routes the value to the right one. "LAPSED" means the LEI registration lapsed, not that the company is gone.
`country`	No	Restrict to the legal address country. ISO 3166-1 alpha-2, e.g. "US", "DE", "JP". Alpha-3 codes and country names are accepted for the common jurisdictions and converted; anything unrecognized is rejected with an error rather than silently returning zero rows.
`page_size`	No	1-200 (default 25)

Output Schema

Name	Required	Description	Default
`total`	Yes	Total number of matching LEI records
`results`	Yes	Matched LEI records with normalized fields

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedJul 30, 2026

changedInput schema / properties / country / description

Previous value: -"Restrict to a jurisdiction (ISO 3166-1 alpha-2, e.g., \"US\", \"DE\")"New value: +"Restrict to the legal address country. ISO 3166-1 alpha-2, e.g. \"US\", \"DE\", \"JP\". Alpha-3 codes and country names are accepted for the common jurisdictions and converted; anything unrecognized is rejected with an error rather than silently returning zero rows."

changedInput schema / properties / query / description

Previous value: -"Legal entity name (full or partial)"New value: +"Legal entity name (full or partial), e.g. \"Apple Inc.\" or \"Siemens Aktiengesellschaft\""

changedInput schema / properties / status / description

Previous value: -"ACTIVE | LAPSED | INACTIVE | PENDING | NULL"New value: +"Entity status (ACTIVE | INACTIVE | NULL) or LEI registration status (ISSUED | LAPSED | ANNULLED | PENDING_TRANSFER | PENDING_ARCHIVAL | DUPLICATE | RETIRED | MERGED). GLEIF keeps these in two different fields; the tool routes the value to the right one. \"LAPSED\" means the LEI registration lapsed, not that the company is gone."

changedInput schema / properties / status / enum

Previous value: -[
-  "ACTIVE",
-  "LAPSED",
-  "INACTIVE",
-  "PENDING",
-  "NULL"
-]New value: +[
+  "ACTIVE",
+  "INACTIVE",
+  "NULL",
+  "ISSUED",
+  "LAPSED",
+  "ANNULLED",
+  "PENDING_TRANSFER",
+  "PENDING_ARCHIVAL",
+  "DUPLICATE",
+  "RETIRED",
+  "MERGED"
+]

Changed2 schema fields changedMay 22, 2026

addedInput schema / examples

Added value: +[
+  {
+    "query": "Apple Inc"
+  },
+  {
+    "country": "DE",
+    "page_size": 50,
+    "query": "Deutsche Bank",
+    "status": "ACTIVE"
+  }
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "results": {
+      "description": "Matched LEI records with normalized fields",
+      "items": {
+        "properties": {
+          "bic": {
+            "description": "Bank Identifier Codes",
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "category": {
+            "description": "Entity category",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "entity_status": {
+            "description": "Entity status (ACTIVE, LAPSED, etc.)",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "gleif_url": {
+            "description": "Direct link to GLEIF record",
+            "type": "string"
+          },
+          "headquarters_address": {
+            "description": "Headquarters address of entity",
+            "properties": {
+              "city": {
+                "description": "City name",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "country": {
+                "description": "ISO country code",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "lines": {
+                "description": "Address lines",
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              },
+              "postal_code": {
+                "description": "Postal code",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "region": {
+                "description": "Region or state",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              }
+            },
+            "type": [
+              "object",
+              "null"
+            ]
+          },
+          "initial_registration": {
+            "description": "ISO date of initial registration",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "isins": {
+            "description": "ISIN codes",
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "jurisdiction": {
+            "description": "ISO jurisdiction code",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "last_update": {
+            "description": "ISO date of last update",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "legal_address": {
+            "description": "Legal address of entity",
+            "properties": {
+              "city": {
+                "description": "City name",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "country": {
+                "description": "ISO country code",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "lines": {
+                "description": "Address lines",
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              },
+              "postal_code": {
+                "description": "Postal code",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "region": {
+                "description": "Region or state",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              }
+            },
+            "type": [
+              "object",
+              "null"
+            ]
+          },
+          "legal_form": {
+            "description": "Legal form ID or description",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "legal_name": {
+            "description": "Official legal entity name",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "lei": {
+            "description": "20-character LEI code",
+            "type": "string"
+          },
+          "managing_lou": {
+            "description": "Managing Local Operating Unit",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "next_renewal": {
+            "description": "ISO date of next renewal",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "other_names": {
+            "description": "Alternative names for the entity",
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "registration_status": {
+            "description": "Registration status",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total": {
+      "description": "Total number of matching LEI records",
+      "type": "number"
+    }
+  },
+  "required": [
+    "total",
+    "results"
+  ],
+  "type": "object"
+}

First observedMay 11, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, and the description adds substantial behavior beyond them: whole-token AND matching against the registered legal name, automatic retries with suffix dropping, word joining, and fuzzy autocomplete, plus match_mode/searched_as reporting so the agent can audit which query produced results.

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

Conciseness5/5

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

Front-loaded with the core action and return shape, then matching caveats and fallback behavior. Dense but every sentence carries actionable information; no filler.

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

Completeness5/5

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

Output schema exists, so return values needn't be explained, yet the description still flags match_mode/searched_as for interpretation. Covers the non-obvious failure mode (abbreviations matching nothing) that an agent would otherwise misdiagnose as zero results.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns extra by explaining the matching semantics of `query` (whole-token AND, registered-name-only, retry fallbacks) that the schema does not. It does not add much on status/country/page_size, which the schema already covers well.

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

Purpose5/5

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

States a specific verb (search) and resource (GLEIF LEI registry) plus the keying field (legal entity name), and describes the returned fields. It is clearly distinguishable from exact-LEI siblings like get_lei or bic_to_lei.

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

Usage Guidelines4/5

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

Explicitly frames the use case: resolving canonical identity across SEC, OpenSanctions, and counterparty databases via the returned LEI. It does not, however, name when to prefer it over siblings such as get_lei, resolve_entity, or company_register_search.

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

All Gleif tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.