# Annalist Financial Statements (remote · annalist.io)

Financial statements, ratios, findings, screens and peer comparisons from official filings. Keyless.

- Trust score: 74/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `annalist.io`: 74/100 (this document), [markdown](https://verifymcp.io/servers/rawsd10-annalist/annalist.md), [page](https://verifymcp.io/servers/rawsd10-annalist/annalist)

## Channel facts

- Endpoint: `https://annalist.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- 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**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 75/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4088 tokens (~227/item across 18 items; 18 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 99% of tool parameters carry a description.
  - Structured output schemas are declared (100% 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 18 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 19 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 Annalist Financial Statements MCP server?

Annalist Financial Statements is a hosted endpoint at https://annalist.io/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 rawsd10-annalist 'https://annalist.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "rawsd10-annalist": {
      "url": "https://annalist.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "rawsd10-annalist": {
      "type": "http",
      "url": "https://annalist.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.rawsd10-annalist]
url = "https://annalist.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "rawsd10-annalist": {
      "type": "remote",
      "url": "https://annalist.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add rawsd10-annalist --url 'https://annalist.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  rawsd10-annalist:
    url: "https://annalist.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "rawsd10-annalist": {
      "Transport": "http",
      "Url": "https://annalist.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add rawsd10-annalist -t streamable-http -u 'https://annalist.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "rawsd10-annalist": {
      "type": "http",
      "url": "https://annalist.io/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.

### 2026-11-05 (score 74, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 3423 → 4088
- [functional] Server version: 1.3.0 → 1.4.0
- [functional] New tool “find_connections”
- [functional] New tool “get_relationships”
- [functional] New tool “search_entities”

### 2026-11-02 (score 73, +1)

- [security] Tool “list_snapshots” rewrote its description, which is the text the model reads
- [security] Tool “get_statement” rewrote its description, which is the text the model reads
- [security] Tool “search” rewrote its description, which is the text the model reads

### 2026-11-01 (score 72, 0)

- [security] Tool “get_ratios” rewrote its description, which is the text the model reads

### 2026-10-31 (score 72, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “screen_companies” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.2.1 → 1.3.0
- [cosmetic] “screen_companies” added an optional parameter “basis”
- [cosmetic] “screen_companies” added an optional parameter “markets”
- [cosmetic] “screen_companies” added an optional parameter “screen”
- [cosmetic] “screen_companies” added an optional parameter “start”

### 2026-10-30 (score 71)

First indexed and scored.

## MCP tools (18)

### `search_companies` (~113 tokens)

Search companies

Find companies covered by Annalist by name, ticker, SEC CIK or id, optionally filtered by country. Returns each company's id (used by the other tools), identifiers, sources and latest snapshot.

Input parameters:

- `country` (string): ISO 3166 country code, for example US, GB, ID, HK or JP
- `limit` (integer): maximum number of companies (default 20)
- `query` (string): part of a name, ticker, CIK or id; leave empty to list all

Output parameters:

- `companies` (array)
- `total` (integer)

### `get_company_overview` (~128 tokens)

Get a company overview

One answer on a company, the first call for a question about it: identity, sector, latest snapshot, revenue and net income of the latest quarter (or fiscal year) with their change against a year earlier, the latest value of each measure of the directory (margins, returns, growth, debt, liquidity) with its period and unit, the current key findings with their source document ids, 3 peers, data quality and links to the page and the workbook.

Input parameters:

- `company` (string, required): company id from search_companies, for example apple or telkom-indonesia

Output parameters:

- `accounting` (string|null)
- `as_of` (object)
- `checks` (object)
- `citation` (object)
- `company` (string)
- `country` (string|null)
- `data_quality` (object|null)
- `documents` (integer)
- `exchange` (string|null)
- `findings` (array)
- `fiscal_year_end` (string|null)
- `industry` (string|null)
- `latest` (object)
- `links` (object)
- `market` (string|null)
- `measures` (object)
- `more` (string)
- `name` (string)
- `peers` (array)
- `published_at` (string|null)
- `sector` (string|null)
- `snapshot` (string)
- `sources` (string|null)
- `template` (string)
- `tickers` (array)

### `get_statement` (~290 tokens)

Get a financial statement

Figures of one statement for one company from its latest snapshot, filtered by period and item. Every row gives its period with start and end dates, whether each value is reported or derived, and the source document ids of its values; item units are in `items`, and the answer names its snapshot for the citation.

Input parameters:

- `at` (string): an ISO date: the snapshot that was the latest on that date, in place of the latest snapshot
- `compact` (boolean): true for the rows with their units only, without the conventions, item definitions and citation format
- `company` (string, required): company id from search_companies, for example apple or mizuho
- `frequency` (string): for income_statement and cash_flow (default annual); other statements have one frequency
- `from` (string): first period: a fiscal year (2024), a fiscal quarter (FY2024 Q2) or an ISO date
- `items` (array): item keys to keep, for example ["revenue", "net_income"]; leave empty for all
- `limit` (integer): maximum rows, latest first kept (default 40, at most 60)
- `statement` (string, required): income_statement, balance_sheet and cash_flow; Mizuho also has capital, npl, shares and annual_highlights
- `to` (string): last period, in the same forms

Output parameters:

- `as_of` (object)
- `citation` (object)
- `company` (string)
- `conventions` (object)
- `frequency` (string)
- `items` (object)
- `name` (string)
- `published_at` (string)
- `rows` (array)
- `rows_matched` (integer)
- `snapshot` (string)
- `statement` (string)
- `truncated` (boolean)

### `get_ratios` (~412 tokens)

Get financial ratios

Ratios computed from a company's latest snapshot by formulas with stable ids (bank.roe, corp.roic). Every value gives its unit, period and the snapshot figures it was computed from, each with its value and source document ids. Banks use the bank template (quarterly values annualised; Mizuho under Japanese GAAP, the other banks under US GAAP or IFRS on the measures their statements give); other companies use the corporate template (annual, quarterly and trailing four quarters, ttm), which includes credit metrics, liquidity, earnings quality and forensic scores; scores, credit reconciliations and the liquidity cover also give their parts, named with their coefficients in the catalogue. A value computed with an estimated input, such as the lease cost of the latest fiscal year for quarters that do not report it, names it in estimates; a ratio that a rule leaves out for the company gives the reason in excluded. Call without ratios to list the catalogue of one frequency.

Input parameters:

- `at` (string): an ISO date: answers when the snapshot that was the latest on that date is the latest one, since ratios are published beside the latest snapshot only
- `category` (string): keep one category, for example Profitability or Credit metrics
- `compact` (boolean): true for the values with their units only, without the conventions, the catalogue entries, the inputs and the citation format
- `company` (string, required): company id from search_companies, for example apple or mizuho
- `frequency` (string): default annual
- `from` (string): first period: a fiscal year (2024), a fiscal quarter (FY2024 Q2) or an ISO date
- `limit` (integer): maximum values, those of the latest periods kept (default 120)
- `ratios` (array): ratio ids or short names, for example ["roe", "corp.operating_margin"]; leave empty for all
- `to` (string): last period, in the same forms

Output parameters:

- `citation` (object)
- `company` (string)
- `conventions` (object)
- `engine` (string)
- `frequency` (string)
- `name` (string)
- `ratios` (object)
- `snapshot` (string)
- `template` (string)
- `truncated` (boolean)
- `values` (array)
- `values_matched` (integer)

### `get_findings` (~206 tokens)

Get key findings

The key findings of a company, written by fixed rules from its figures: each a sentence ready to quote with its rule, claim, state (New, Confirmed, Strengthened, Weakened), the period, the measure and the figures it states with their source document ids. Modules: overview (growth, margins, returns, net debt), credit (debt against the S&P benchmark bands), liquidity, quality (cash backing of earnings) and scores (Altman, Beneish, Piotroski). Pass history for the record of each finding across snapshots, and retired for findings that no longer apply.

Input parameters:

- `company` (string, required): company id from search_companies, for example apple or mizuho
- `history` (boolean): true to add the records of each finding: state, change type, period and snapshot
- `module` (string): keep the findings of one module
- `retired` (boolean): true to add the findings that no longer apply

Output parameters:

- `as_of` (object)
- `citation` (object)
- `company` (string)
- `conventions` (object)
- `corrections` (array)
- `count` (integer)
- `findings` (array)
- `findings_version` (string)
- `modules` (array)
- `name` (string)
- `page` (string)
- `snapshot` (string)

### `screen_companies` (~573 tokens)

Screen companies

Screen the companies of the coverage as the Screener page of Annalist does, or rank them by one measure. With screen, the conditions of the page joined by commas: roic.gt.12 (latest value above 12; lt below), roic.gt.12.y5 (above 12 in each of the last 5 fiscal years), om.up.3 (higher than the year before in each of the last 3 fiscal years; dn lower), dte.chg.gt.0.5.y1 (change over the last fiscal year above 0.5), roic.top.25 (among the highest 25% of the companies screened; bot the lowest; .s within the sector) and band.in.minimal-modest (credit and quality signals: band, cover, netdebt, fcf, backing, altman, piotroski, beneish). start runs a starting screen such as rising-debt or high-returns. Each company comes with the figures behind each condition and its page, and page links the same screen for a person. Without screen, where and sort filter and rank by the latest value of ratio ids with a frequency, as corp.roic@ttm or corp.current_ratio@quarterly; an amount such as corp.net_debt is ranked within its currency. Call without arguments to list the measures and the starting screens.

Input parameters:

- `basis` (string): with screen: latest (default) for the last 4 quarters where reported, fy for the latest fiscal year of every company
- `country` (string): ISO 3166 country code, for example US, GB, ID or HK
- `currency` (string): keep the companies that report in one currency, for example USD
- `industry` (string): part of an industry name, for example Semiconductors or Banks
- `limit` (integer): maximum companies (default 20)
- `markets` (array): with screen: ISO country codes, for example ["SG", "ID"]
- `order` (string): desc (default) for the highest first
- `screen` (string): the conditions of a screen, for example roic.gt.12.y5,nde.lt.2 or band.in.significant-aggressive
- `sector` (string): part of a sector name, for example Technology or Health care
- `sort` (string): the measure to rank by, for example corp.operating_margin@ttm
- `start` (string): a starting screen of the Screener page, for example high-returns, rising-debt or credit-watch
- `template` (string)
- `where` (array): conditions that every company meets, for example [{"measure": "corp.roic@ttm", "min": 15}]

Output parameters:

- `basis` (string)
- `companies` (array)
- `conditions` (array)
- `filters` (object)
- `matched` (integer)
- `measures` (object)
- `measures_available` (array)
- `note` (string)
- `page` (string)
- `rules_version` (string)
- `screen` (string)
- `screened` (integer)
- `screens_available` (array)
- `start` (object)
- `truncated` (boolean)
- `without_value` (integer)

### `compare_companies` (~288 tokens)

Compare companies on calendar quarters

2 to 4 companies side by side, aligned on calendar quarters as Annalist Compare places their fiscal periods, so that companies whose fiscal years end in different months stand in the same quarter. Measures are ratio ids (corp.operating_margin, corp.roic, corp.revenue_growth, bank.roe; short names such as roic work) or statement items (revenue, net_income, total_assets, cfo). Ratios use the last 4 quarters where the ratio has them, else the quarter; a company that reports fiscal years only gives fiscal years. Each value gives the company's fiscal period, and each statement value its source document ids. Amounts stay in the currency of each company.

Input parameters:

- `companies` (array, required): 2 to 4 company ids from search_companies
- `frequency` (string): the form of every ratio, in place of the last 4 quarters where a ratio has them; annual compares fiscal years
- `from` (string): first calendar quarter: CY2025 Q1, a year (2025) or an ISO date
- `measures` (array, required): 1 to 6 ratio ids or statement item keys, for example ["corp.operating_margin", "revenue"]
- `quarters` (integer): the latest calendar quarters kept (default 8)
- `to` (string): last calendar quarter, in the same forms

Output parameters:

- `citation` (object)
- `companies` (array)
- `conventions` (object)
- `latest_common_quarter` (string|null)
- `measures` (object)
- `notes` (array)
- `quarters` (array)
- `quarters_matched` (integer)
- `truncated` (boolean)

### `get_events` (~182 tokens)

Get corporate events

Corporate events of a company found by fixed rules in its filings: acquisitions, disposals, spin-offs, discontinued operations, reorganisations, stock splits, restatements, name changes and changes of fiscal year, each with its date, fiscal period, a sentence, the counterparty and amount where the filing names them, and its source document ids. Events are recorded for companies that file with the SEC.

Input parameters:

- `at` (string): an ISO date: the snapshot that was the latest on that date, in place of the latest snapshot
- `company` (string, required): company id from search_companies, for example apple or mizuho
- `from` (string): first date: a year (2024) or an ISO date
- `to` (string): last date, in the same forms
- `types` (array): keep these event types

Output parameters:

- `as_of` (object)
- `citation` (object)
- `company` (string)
- `events` (array)
- `matched` (integer)
- `name` (string)
- `note` (string)
- `snapshot` (string)
- `total` (integer)
- `types` (object)

### `get_data_quality` (~146 tokens)

Get data quality

How far the figures of a company are proven: the values published, confirmed by a check, confirmed by a second document, derived from reported figures and withheld, with the meaning of each measure; every withheld value with its reason and documents; and every restated figure with the first, latest and published value, each with its document and filing date.

Input parameters:

- `at` (string): an ISO date: the snapshot that was the latest on that date, in place of the latest snapshot
- `company` (string, required): company id from search_companies, for example apple or mizuho
- `limit` (integer): maximum withheld values and restated figures each (default 50)

Output parameters:

- `as_of` (object)
- `citation` (object)
- `company` (string)
- `conventions` (object)
- `measures` (object|null)
- `measures_note` (string)
- `name` (string)
- `page` (string)
- `restated` (array)
- `restated_total` (integer)
- `snapshot` (string)
- `truncated` (boolean)
- `withheld` (array)
- `withheld_total` (integer)

### `get_snapshot_info` (~119 tokens)

Get snapshot information

The latest snapshot of a company: as-of period, release date and time of publication, coverage, conventions (units, signs, fiscal calendar), validation summary, available statements, files with SHA-256 and the citation format. With at, the snapshot that was the latest on that date (point in time).

Input parameters:

- `at` (string): an ISO date: the snapshot that was the latest on that date, in place of the latest snapshot
- `company` (string, required): company id from search_companies, for example apple or mizuho

Output parameters:

- `as_of` (object)
- `citation` (object)
- `company` (object)
- `files` (array)
- `published_at` (string)
- `snapshot` (string)
- `statements` (array)

### `list_snapshots` (~91 tokens)

List published snapshots

Every snapshot that the site has published for a company, oldest first, with its as-of period, dataset hash and time of publication: the point-in-time record of the coverage. Its dates are values of the at parameter of the other tools, which then return the figures as they stood on that date.

Input parameters:

- `company` (string, required): company id from search_companies, for example apple or mizuho

Output parameters:

- `company` (string)
- `conventions` (object)
- `count` (integer)
- `latest` (string)
- `name` (string)
- `snapshots` (array)

### `get_sources` (~156 tokens)

Get source documents

Source documents of a company's latest snapshot: kind, period, release or filing date (indexed: the date an index added a report that states no date of publication), URL of the official document or of the search page of its store, and SHA-256 of the file used. Pass the document ids found in a statement's sources to resolve them.

Input parameters:

- `at` (string): an ISO date: the snapshot that was the latest on that date, in place of the latest snapshot
- `company` (string, required): company id from search_companies, for example apple or mizuho
- `ids` (array): document ids, for example ["10-K:0000320193-25-000079"]; leave empty for all

Output parameters:

- `citation` (object)
- `company` (string)
- `documents` (array)
- `snapshot` (string)

### `run_buyout` (~242 tokens)

Run a buyout model

Run the buyout model 1.0 of Annalist Deal Lab on a company's published figures, at its starting values or with the caller's assumptions under the keys of the address of the page (entry, exit_mult, years, debt, growth, margin, tax, base and the others that the starting values list). Returns the returns, sources and uses, the debt schedule, the covenants and the checks of the model, optionally the 3 solvers, every input with its source document ids, and the address of the same deal on the site. Shares and rates are fractions (0.2 for 20%) and multiples are times EBITDA. The result is arithmetic on published figures and the caller's assumptions: it values no company, recommends no transaction and forecasts nothing.

Input parameters:

- `assumptions` (object): assumptions to change, for example {"entry": 8, "debt": 4}; leave out for the starting values
- `company` (string, required): company id from search_companies, for example apple
- `solvers` (boolean): also return the highest entry multiple for the target return, the growth it needs and the debt capacity

Output parameters:

- `address` (string)
- `assumptions` (object)
- `base`
- `citation` (string)
- `company` (string)
- `computed` (string)
- `currency`
- `debt_schedule` (object)
- `failed_checks`
- `inputs` (object|null)
- `model` (object)
- `name` (string)
- `ok` (boolean)
- `projection` (object)
- `return_bridge` (object|null)
- `returns` (object|null)
- `snapshot` (string)
- `solvers` (object)
- `sources_and_uses` (object)

### `search_entities` (~162 tokens)

Search the entities of Atlas

Find a company, a bank or another legal entity in Atlas, the map of the relationships between companies, by part of its name, its LEI or the id of a covered company. Returns each entity's id (used by get_relationships and find_connections), its country, LEI, the covered company that it is or whose group it belongs to (Citibank, N.A. to citigroup), and its number of links.

Input parameters:

- `country` (string): ISO 3166 country code, for example US, SG or JP
- `limit` (integer): maximum number of entities (default 20)
- `query` (string): part of a name, an LEI or a company id, for example JPMorgan Chase Bank or boeing

Output parameters:

- `entities` (array)
- `measure` (object)
- `note` (string)
- `total` (integer)

### `get_relationships` (~265 tokens)

Get the relationships of an entity

The links of one entity in Atlas, in both directions: the lenders of a company and the borrowers of a bank (with the commitment of each lender under each credit agreement where its schedule proves it), the major customers and suppliers with their share of revenue, owners and holdings with the interest, collaboration partners and named related parties. Every link gives its summary, the class of its evidence (stated by one party, confirmed by both, or stated by the register of legal entities), each claim with the part of the document that states it, and the documents with their addresses. A covered company also gets the links of the entities of its group (group: true, the default). Probable links are listed apart.

Input parameters:

- `direction` (string): from: links where the entity lends, sells or owns; to: where it borrows, buys or is owned (default both)
- `entity` (string, required): entity id from search_entities, for example boeing, citigroup or dbs-bank-ltd
- `group` (boolean): include the links of the entities of the group of a covered company (default true)
- `kinds` (array): kinds of link to return (default every kind)
- `limit` (integer): maximum number of links (default 100)

Output parameters:

- `as_of` (string|null)
- `citation` (object)
- `conventions` (object)
- `entity` (object)
- `group_entities` (array)
- `kinds` (object)
- `links` (array)
- `matched` (integer)
- `page` (string)
- `probable` (array)
- `truncated` (boolean)

### `find_connections` (~172 tokens)

Find the connections of 2 entities

The shortest chain of links between 2 entities of Atlas, in either direction, and the counterparties that they share (the banks that lend to both, the customers of both, a common owner), each link with its summary, evidence and document ids. By default an entity of a covered group stands as its group, so that 2 banks of one group count as one lender.

Input parameters:

- `from` (string, required): entity id from search_entities, for example boeing
- `group` (boolean): draw an entity of a covered group as its group (default true)
- `kinds` (array): kinds of link to follow (default every kind)
- `max_links` (integer): longest chain to look for (default 4)
- `to` (string, required): entity id from search_entities, for example caterpillar

Output parameters:

- `citation` (object)
- `from` (object|null)
- `group` (boolean)
- `kinds` (array)
- `links_in_path` (integer|null)
- `note` (string)
- `page` (string)
- `path` (array|null)
- `shared` (array)
- `shared_total` (integer)
- `to` (object|null)

### `search` (~106 tokens)

Search documents

Search the documents of Annalist for a question in words, as ChatGPT connectors and deep research do: the overview, key findings, statements and ratios of the companies that the question names, or the overviews of the companies of an industry or sector it names. Returns ids for fetch, titles and the address of each page. The company ids of the other tools come from search_companies.

Input parameters:

- `query` (string, required): the question or keywords, for example Apple revenue growth or semiconductor margins

Output parameters:

- `results` (array)

### `fetch` (~85 tokens)

Fetch a document

The full text of one document that search returned (an overview, key findings, a statement or the ratios of one frequency of a company), as JSON with its figures, units, periods and source document ids, with the address of its page for the citation.

Input parameters:

- `id` (string, required): a document id from search, for example company:apple or statement:apple:pl_annual

Output parameters:

- `id` (string)
- `metadata` (object)
- `text` (string)
- `title` (string)
- `url` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/rawsd10-annalist/annalist#diagnostics

## Score history

- 2026-11-05: 74
- 2026-11-04: 73
- 2026-11-03: 73
- 2026-11-02: 73
- 2026-11-01: 72
- 2026-10-31: 72
- 2026-10-30: 71

## Common questions

### What is the Annalist Financial Statements MCP server?

Annalist Financial Statements is an MCP server listed in the public MCP registry as io.github.rawsd10/annalist. Financial statements, ratios, findings, screens and peer comparisons from official filings. Keyless. This page covers its hosted endpoint (https://annalist.io/mcp).

### Is the Annalist Financial Statements MCP server safe to use?

Annalist Financial Statements scores 74 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 Annalist Financial Statements MCP server expose?

Annalist Financial Statements exposes 18 tools: search_companies, get_company_overview, get_statement, get_ratios, get_findings, and 13 more. Their descriptions and schemas cost roughly 3,736 tokens of context every time the server is loaded.

### Does the Annalist Financial Statements MCP server require authentication?

No. We connected to Annalist Financial Statements without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Annalist Financial Statements MCP server still maintained?

Annalist Financial Statements 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://annalist.io/mcp
- Website: https://annalist.io/agents/
- Changelog RSS feed: https://verifymcp.io/servers/rawsd10-annalist/annalist.xml
- Changelog JSON feed: https://verifymcp.io/servers/rawsd10-annalist/annalist.json
- HTML version of this page: https://verifymcp.io/servers/rawsd10-annalist/annalist