GLEIF MCP — Global Legal Entity Identifier Foundation (free, no auth)
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add mcp-gleif -- npx -y @pipeworx/mcp-gleif{
"mcpServers": {
"mcp-gleif": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-gleif"]
}
}
}MCP Servers overview
# @pipeworx/gleif
Global Legal Entity Identifier Foundation MCP — LEI lookup, ISIN/BIC-to-entity mapping, and corporate hierarchy, no auth.
Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1686+ live data sources.
## Tools
- `search_lei(query, country?, status?, page_size?)` — fuzzy entity-name search. If `country` narrows the result to nothing, the filter is dropped and the response says so via `country_filter_dropped` — GLEIF filters on the *registered legal address*, which often is not where the entity operates (no Sberbank-named record has a Russian one; they sit in CY/SK/LU/GB).
- `get_lei(lei)` — full Level 1 record: legal name, addresses, jurisdiction, legal form, and LEI registration status. Accepts a company **name** as well as a 20-character LEI; a resolved name is echoed back as `resolved_from_name`.
- `get_lei_relationships(lei)` — Level 2 direct parent, ultimate parent, direct children (one hop).
- `isin_to_lei(isin)` — resolve a security's ISIN to the legal entity that issued it (LEI + legal name). A valid-but-unmapped ISIN is reported as `mapped: false, reason: "isin_unmapped"` — the mapping lags new issuance, so unmapped ≠ nonexistent.
- `lei_to_isins(lei)` — all ISINs issued by an entity (LEI or company name accepted). Returns the full set — one entity issues many securities.
- `bic_to_lei(bic)` — resolve a SWIFT/BIC (8 or 11 chars) to the bank's legal entity. 8-char codes are padded to the `XXX` head-office form (GLEIF's filter matches 11-char BICs only); a branch BIC with no mapping of its own falls back to the head office and says so.
- `lei_hierarchy_tree(lei, depth?)` — multi-hop ownership: ancestor chain up to the ultimate parent plus a breadth-first subsidiary tree (depth 1–4, default 2, node budget 150/call).
- `gleif_group_members(lei, limit?)` — the WHOLE consolidated group in one call, across every jurisdiction. Pass any member (LEI or name); the tool climbs to the ultimate accounting-consolidation parent and returns every entity that reports it, every direct-parent descendant, and their international branches. `member_count`, `jurisdiction_count` and `by_jurisdiction` always cover the full group; the member list is capped at `limit` (default 300, max 2000) and says when it is. Siemens AG: 572 reported subsidiaries, matching GLEIF's own ultimate-children count. Fund-management links are not ownership and are excluded. Carries `data_as_of`.
- `gleif_lei_screen(jurisdiction, registration_status?, entity_status?, category?, event_type?, since_days?, name_contains?, limit?, offset?)` — bulk screen across all ~3.4M LEIs: e.g. every LEI in `DE` that lapsed in the last 30 days, Delaware (`US-DE`) entities retired this quarter, UK entities whose latest event is a merger. A country code includes its subdivisions. `since_days` applies to `status_date` (LAPSED = the renewal date missed; RETIRED/ANNULLED = entity expiration date, else last update; ISSUED = initial registration) or, with `event_type`, to the event date. `total` is exact up to 100,000. GLEIF records a merger as `RETIRED` plus a `MERGERS_AND_ACQUISITIONS`/`ABSORPTION` event with `successor_lei` — `MERGED` is refused with that explanation rather than answered with zero rows. Sole-proprietor names are withheld in bulk results (they name individuals). Carries `data_as_of`.
## Data source
`gleif_group_members` and `gleif_lei_screen` answer from the **GLEIF golden copy** (Level 2 relationship records and Level 1 entity reference data, published three times a day at goldencopy.gleif.org), refreshed daily. `data_as_of` in each response is the GLEIF publish time the answer reflects.
**Licence.** GLEIF LEI Data Terms of Use, section II: *"The data available through the Access Service are provided under the CC0 licence"* ([terms](https://www.gleif.org/en/meta/lei-data-terms-of-use), read 2026-09-30).
The other tools:
`https://api.gleif.org/api/v1/` — public JSON:API, no key required. ISIN and BIC joins use GLEIF's official ISIN-to-LEI and BIC-to-LEI mapping files as served through the same API (`filter[isin]`, `filter[bic]`, `/lei-records/{lei}/isins`).
## Passing an LEI
Every tool that takes an `lei` argument also takes a company **name** — the name is resolved
against the registry and the match is returned alongside the answer. Pass the name whenever
that is what you have.
**Never construct an LEI code.** A guessed 20-character string that happens to be a real LEI
belongs to some other company, and GLEIF returns its record with nothing to indicate the wrong
entity was fetched — a request for Wirecard AG once came back as Baader Bank
Aktiengesellschaft. Codes are checked against the ISO 17442 (ISO 7064 MOD 97-10) check digits
before any request is made, and a code that fails is rejected with a message naming
`search_lei`; that catches roughly 96 of every 97 invented codes, but not one that collides
with a live record, which is why the name path exists.
## Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
```json
{
"mcpServers": {
"gleif": {
"url": "https://gateway.pipeworx.io/gleif/mcp"
}
}
}
```
### What this endpoint actually serves
`tools/list` at `https://gateway.pipeworx.io/gleif/mcp` returns the tools in the table
above **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,
`discover_tools`, `search_within`, `remember`/`recall` and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's `initialize` response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
`ask_pipeworx`, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed
directly, instead of just this one's:
```json
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
```
Both URLs reach the same gateway and the same 1686+ data sources. The
only difference is which pack's tools are listed **directly**; `ask_pipeworx`
reaches all of them from either one.
## No MCP client? Call it over HTTP
```bash
curl -X POST https://gateway.pipeworx.io/v1/tools/search_lei \
-H 'Content-Type: application/json' \
-d '{"query":"Apple Inc"}'
```
No account needed for the first calls. Inspect any tool: `GET https://gateway.pipeworx.io/v1/tools/search_lei`. Find one: `POST https://gateway.pipeworx.io/v1/tools/search_packs` with `{"query":"..."}`.
## Standalone (no gateway account)
This package also runs as a local stdio MCP server — no Pipeworx account, no
gateway round-trip:
```json
{
"mcpServers": {
"gleif": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-gleif"]
}
}
}
```
Or run it directly to confirm it starts:
```bash
npx -y @pipeworx/mcp-gleif
```
It speaks MCP over stdin/stdout and answers `initialize`/`tools/list`/`tools/call`
for **only** this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.
## Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English —
this works on the pack endpoint above as well as on the full gateway:
```
ask_pipeworx({ question: "your question about Gleif data" })
```
The gateway picks the right tool and fills the arguments automatically.
## More
- [Docs and guides](https://pipeworx.io/docs)
- [pipeworx.io](https://pipeworx.io)
## License
MIT
What people ask about mcp-gleif
What is pipeworx-io/mcp-gleif?
+
pipeworx-io/mcp-gleif is mcp servers for the Claude AI ecosystem. GLEIF MCP — Global Legal Entity Identifier Foundation (free, no auth) It has 0 GitHub stars and its last recorded update is dated 2026-09-30.
How do I install mcp-gleif?
+
You can install mcp-gleif by cloning the repository (https://github.com/pipeworx-io/mcp-gleif) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is pipeworx-io/mcp-gleif safe to use?
+
Our security agent has analyzed pipeworx-io/mcp-gleif and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains pipeworx-io/mcp-gleif?
+
pipeworx-io/mcp-gleif is maintained by pipeworx-io. The last recorded GitHub activity is dated 2026-09-30, with 0 open issues.
Are there alternatives to mcp-gleif?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy mcp-gleif to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/pipeworx-io-mcp-gleif)<a href="https://claudewave.com/repo/pipeworx-io-mcp-gleif"><img src="https://claudewave.com/api/badge/pipeworx-io-mcp-gleif" alt="Featured on ClaudeWave: pipeworx-io/mcp-gleif" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
The fastest path to AI-powered full stack observability, even for lean teams.