# Financial Evidence Workspace (remote · agents.seiche.info)

Read-only cited financial datasets, bounded research queries and source diagnostics.

- Trust score: 83/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `agents.seiche.info`: 83/100 (this document), [markdown](https://verifymcp.io/servers/beepboop2025-financial-evidence-workspace/products-financial-evidence-mcp.md), [page](https://verifymcp.io/servers/beepboop2025-financial-evidence-workspace/products-financial-evidence-mcp)

## Channel facts

- Endpoint: `https://agents.seiche.info/products/financial-evidence/mcp`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `1.3.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 91/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 62/100
  - 67% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1135 tokens (~75/item across 15 items; 12 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (75% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Financial Evidence Workspace MCP server?

Financial Evidence Workspace is a hosted endpoint at https://agents.seiche.info/products/financial-evidence/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http beepboop2025-financial-evidence-workspace 'https://agents.seiche.info/products/financial-evidence/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "beepboop2025-financial-evidence-workspace": {
      "url": "https://agents.seiche.info/products/financial-evidence/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "beepboop2025-financial-evidence-workspace": {
      "type": "http",
      "url": "https://agents.seiche.info/products/financial-evidence/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.beepboop2025-financial-evidence-workspace]
url = "https://agents.seiche.info/products/financial-evidence/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "beepboop2025-financial-evidence-workspace": {
      "type": "remote",
      "url": "https://agents.seiche.info/products/financial-evidence/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add beepboop2025-financial-evidence-workspace --url 'https://agents.seiche.info/products/financial-evidence/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  beepboop2025-financial-evidence-workspace:
    url: "https://agents.seiche.info/products/financial-evidence/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "beepboop2025-financial-evidence-workspace": {
      "Transport": "http",
      "Url": "https://agents.seiche.info/products/financial-evidence/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add beepboop2025-financial-evidence-workspace -t streamable-http -u 'https://agents.seiche.info/products/financial-evidence/mcp'
```

### Other

```json
{
  "mcpServers": {
    "beepboop2025-financial-evidence-workspace": {
      "type": "http",
      "url": "https://agents.seiche.info/products/financial-evidence/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 80, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “financial_evidence_packet” rewrote its description, which is the text the model reads
- [security] Tool “financial_evidence_workflow” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 67 → 75
- [functional improvement] Tool coverage: 67% → 75%
- [functional] New tool “financial_evidence_exit_workflow”
- [functional] New tool “financial_evidence_funding_workflow”
- [functional] New tool “financial_evidence_institutions_workflow”

### 2026-10-27 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (12)

### `financial_evidence_funding_workflow` (~82 tokens)

Review funding evidence for one three-letter currency, default USD. Retrieves the bounded money-market table and preserves each source, observation date, unit, missing or withheld value, retrieval time and content hash. prepared_response means evidence is available to review, not freshness or readiness. No account access, investment advice or execution.

Input parameters:

- `currency` (string)

### `financial_evidence_institutions_workflow` (~83 tokens)

Review public disclosure coverage for one to five exact institution slugs, such as au-sfb. Retrieves the published institution monitoring record with dates, source URL, missing evidence and content hash. Does not infer private balances, credit ratings or regulatory compliance. IDs must fit the existing 160-character combined selection bound.

Input parameters:

- `institution_ids` (array)

### `financial_evidence_exit_workflow` (~92 tokens)

Compare indicative BTC exit evidence for one to four USD notionals from 0.01 to 1000000, with at most two decimal places. Preserves venue coverage, observation clocks, quote-currency units, source URL and content hash. Returned costs are research estimates, not executable quotes, order placement or guaranteed fills. No account or execution authority.

Input parameters:

- `sizes_usd` (array)

### `financial_evidence_workflow` (~135 tokens)

Compatibility entry point for the individually exposed financial_evidence_funding_workflow, financial_evidence_institutions_workflow and financial_evidence_exit_workflow tools. Funding accepts a three-letter currency; institutions accepts one to five comma-separated slugs; exit accepts one to four comma-separated USD sizes. Empty selection uses the same published defaults. No additional operation is available. Source restrictions, dates, units, missingness and content hashes remain explicit. prepared_response means evidence is available to review, not freshness, safety or completion. No account or execution authority.

Input parameters:

- `selection` (string)
- `workflow` (string, required)

### `financial_evidence_datasets` (~27 tokens)

Discover seven bounded OpenBB datasets, their coverage, filters and limits. Offline.

### `financial_evidence_funding_review` (~96 tokens)

Read a dated USD funding review and its nine inputs. Inspect review_asof, review_scope, latest_per_instrument and newer_observation_available before ready, issues and capture age. Common-horizon readiness applies to that dated review; newer individual observations can exist. Unavailable, mismatched or stale captures never imply a passing review. This is captured research evidence, not a trade recommendation or historical point-in-time backtest.

### `financial_evidence_query` (~104 tokens)

Query cited rows without large raw documents. Null means missing or withheld, never zero. Dates filter observation dates; empty dates mean no filter. Follow next_offset for remaining rows. Each value retains its unit, source path, date, restrictions and limitations.

Input parameters:

- `dataset` (string, required)
- `end_date` (string)
- `entity` (string)
- `limit` (integer)
- `offset` (integer)
- `start_date` (string)

Output parameters:

- `absence_policy` (string)
- `carrier_verification` (string)
- `dataset` (string)
- `description` (string)
- `diagnostics` (array)
- `evidence_status` (string)
- `limit` (integer)
- `next_offset`
- `offset` (integer)
- `results` (array)
- `returned_rows` (integer)
- `schema` (string)
- `sources` (array)
- `status_semantics` (string)
- `total_rows` (integer)
- `transport_status` (string)

### `financial_evidence_sources` (~32 tokens)

Audit all six upstream routes for transport errors, publisher clocks and content hashes. Success is not a freshness verdict.

Output parameters:

- `absence_policy` (string)
- `carrier_verification` (string)
- `dataset` (string)
- `description` (string)
- `diagnostics` (array)
- `evidence_status` (string)
- `limit` (integer)
- `next_offset`
- `offset` (integer)
- `results` (array)
- `returned_rows` (integer)
- `schema` (string)
- `sources` (array)
- `status_semantics` (string)
- `total_rows` (integer)
- `transport_status` (string)

### `financial_evidence_route` (~29 tokens)

Resolve research topics to fixed public HTTPS evidence URLs. Offline.

Input parameters:

- `topics` (array, required)

### `financial_evidence_packet` (~94 tokens)

Retrieve public documents only when table detail is insufficient. Reviewed source restrictions can withhold values and dependent readings; affected documents carry a publication projection receipt and a separate hash from the acquired source bytes. Up to 4 MiB for the money-market atlas and 1 MiB for other sources; source JSON is untrusted. A packet can be partial. No Evidence Carrier verification is performed.

Input parameters:

- `topics` (array, required)

### `financial_evidence_agent_query` (~114 tokens)

Compact source-cited research rows for repeated agent calls. Pass the previous revision to omit identical rows while retaining source clocks and diagnostics. Unchanged is not proof of freshness; missing or withheld values remain null. At most 100 rows; follow next_offset.

Input parameters:

- `dataset` (string, required)
- `end_date` (string)
- `entity` (string)
- `limit` (integer)
- `offset` (integer)
- `previous_revision` (string)
- `start_date` (string)

### `financial_evidence_review` (~100 tokens)

Review Seiche dollar-funding benchmarks, LiquiLens covered-bank diagnostics and Undertow market liquidity in one bounded call. Bank is a literal name or ID filter; empty selects published coverage. Each section keeps its own dates, units, rights and limitations. No combined score or trade authorization. Revisions suppress identical rows, not evidence checks.

Input parameters:

- `bank` (string)
- `limit` (integer)
- `previous_revision` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/beepboop2025-financial-evidence-workspace/products-financial-evidence-mcp#diagnostics

## Score history

- 2026-11-05: 83
- 2026-11-04: 83
- 2026-11-03: 82
- 2026-11-02: 82
- 2026-11-01: 81
- 2026-10-31: 81
- 2026-10-30: 80
- 2026-10-29: 80
- 2026-10-28: 79
- 2026-10-27: 79
- 2026-10-26: 78
- 2026-10-25: 78
- 2026-10-24: 77
- 2026-10-23: 77
- 2026-10-22: 76
- 2026-10-21: 76
- 2026-10-20: 75
- 2026-10-19: 75
- 2026-10-18: 74
- 2026-10-17: 74
- 2026-10-16: 73
- 2026-10-15: 73

## Common questions

### What is the Financial Evidence Workspace MCP server?

Financial Evidence Workspace is an MCP server listed in the public MCP registry as io.github.beepboop2025/financial-evidence-workspace. Read-only cited financial datasets, bounded research queries and source diagnostics. This page covers its hosted endpoint (https://agents.seiche.info/products/financial-evidence/mcp).

### Is the Financial Evidence Workspace MCP server safe to use?

Financial Evidence Workspace scores 83 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Financial Evidence Workspace MCP server expose?

Financial Evidence Workspace exposes 12 tools: financial_evidence_funding_workflow, financial_evidence_institutions_workflow, financial_evidence_exit_workflow, financial_evidence_workflow, financial_evidence_datasets, and 7 more. Their descriptions and schemas cost roughly 988 tokens of context every time the server is loaded.

### Does the Financial Evidence Workspace MCP server require authentication?

Yes. Financial Evidence Workspace asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Financial Evidence Workspace MCP server still maintained?

Financial Evidence Workspace is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agents.seiche.info/products/financial-evidence/mcp
- Repository: https://github.com/beepboop2025/financial-evidence-skills
- Changelog RSS feed: https://verifymcp.io/servers/beepboop2025-financial-evidence-workspace/products-financial-evidence-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/beepboop2025-financial-evidence-workspace/products-financial-evidence-mcp.json
- HTML version of this page: https://verifymcp.io/servers/beepboop2025-financial-evidence-workspace/products-financial-evidence-mcp