Connect Seiche, LiquiLens and Undertow source data and your agent gets 8 tools, among them research_analysis, research_catalog, research_entities. It answers at https://api.seiche.info/api/v2/research-data/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 27 September 2026; the last check, on 11 November 2026, succeeded.
Funding histories, bank filings and settlement data with source receipts, units and capture clocks.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
research_analysis | Read descriptive funding, institution concentration and settlement analysis with input references and limits. Inputs: product |
research_catalog | Discover scoped funding, institution and chain-settlement datasets with coverage and rights. Inputs: product |
research_entities | Find regulator identifiers for institutions; names are not fuzzy-joined across regimes. Inputs: dataset, q, limit, offset |
research_observations | Read cited observations or a captured historical vintage. Earlier point-in-time availability is not assumed. Inputs: dataset, series, entity, start, end, as_known_at |
research_series | Search the metric catalog and native unit definitions in a dataset. Inputs: dataset, q, limit, offset |
research_series_summary | Analyze the latest captured series for one exact entity, with adjacent change, trailing-window missingness, native units and source receipts. Current analytics are withheld for stale, unavailable or unverified inputs. Inputs: dataset, series, entity, window |
research_tracked_institutions | Search the existing Indian dossier and RBI registry populations, retaining financial-evidence gaps and source clocks. Populations overlap and are not a global census. Inputs: scope, q, limit, offset |
research_workspace | Read the same coverage, source freshness, gaps and descriptive overview as the website. Compare snapshot_id across REST/MCP; independent source clocks remain explicit. Inputs: product |
Every block below points at https://api.seiche.info/api/v2/research-data/mcp. Pick your client and copy.
claude mcp add --transport http seiche-liquilens-and-undertow-so https://api.seiche.info/api/v2/research-data/mcp
{
"mcpServers": {
"seiche-liquilens-and-undertow-so": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.seiche.info/api/v2/research-data/mcp"]
}
}
}{
"mcpServers": {
"seiche-liquilens-and-undertow-so": {
"url": "https://api.seiche.info/api/v2/research-data/mcp"
}
}
}{
"servers": {
"seiche-liquilens-and-undertow-so": {
"type": "http",
"url": "https://api.seiche.info/api/v2/research-data/mcp"
}
}
}{
"context_servers": {
"seiche-liquilens-and-undertow-so": {
"url": "https://api.seiche.info/api/v2/research-data/mcp"
}
}
}{
"mcpServers": {
"seiche-liquilens-and-undertow-so": {
"serverUrl": "https://api.seiche.info/api/v2/research-data/mcp"
}
}
}{
"mcpServers": {
"seiche-liquilens-and-undertow-so": {
"url": "https://api.seiche.info/api/v2/research-data/mcp"
}
}
}name: Seiche, LiquiLens and Undertow source data
version: 0.0.1
schema: v1
mcpServers:
- name: Seiche, LiquiLens and Undertow source data
type: streamable-http
url: https://api.seiche.info/api/v2/research-data/mcp{
"mcpServers": {
"seiche-liquilens-and-undertow-so": {
"httpUrl": "https://api.seiche.info/api/v2/research-data/mcp"
}
}
}{
"mcpServers": {
"seiche-liquilens-and-undertow-so": {
"type": "http",
"url": "https://api.seiche.info/api/v2/research-data/mcp"
}
}
}{
"mcpServers": {
"seiche-liquilens-and-undertow-so": {
"url": "https://api.seiche.info/api/v2/research-data/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.seiche.info%2Fapi%2Fv2%2Fresearch-data%2Fmcp&type=streamable_http&id=seiche-liquilens-and-undertow-so&name=Seiche%2C%20LiquiLens%20and%20Undertow%20source%20data
It answered our last check on 11 November 2026 in 66 ms. Over 4 checks since 27 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
8, as returned by the server's own tools/list on 16 November 2026: research_analysis, research_catalog, research_entities, research_observations, research_series, research_series_summary, research_tracked_institutions, research_workspace.
It answered our last check on 11 November 2026 in 66 ms. Over 4 checks since 27 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.seiche.info/api/v2/research-data/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.beepboop2025. Endpoint host: api.seiche.info. ARD identifier: urn:air:io.github.beepboop2025:mcp:financial-source-data.
First indexed 26 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.