# SOTA2 — AI Solution Rankings (remote · www.sota2.com)

Compare published AI solution rankings, company facts and research benchmarks with sources.

- Trust score: 68/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `www.sota2.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/leo9-sota2/www.md), [page](https://verifymcp.io/servers/leo9-sota2/www)

## Channel facts

- Endpoint: `https://www.sota2.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.6`

## 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**: 58/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2200 tokens (~314/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 7 days we've observed: 6 tool removals, 0 breaking changes, 0 auth/transport breaks, 2 additions.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 79% 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 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 SOTA2 — AI Solution Rankings MCP server?

SOTA2 — AI Solution Rankings is a hosted endpoint at https://www.sota2.com/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 leo9-sota2 'https://www.sota2.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "leo9-sota2": {
      "url": "https://www.sota2.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "leo9-sota2": {
      "type": "http",
      "url": "https://www.sota2.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.leo9-sota2]
url = "https://www.sota2.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "leo9-sota2": {
      "type": "remote",
      "url": "https://www.sota2.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add leo9-sota2 --url 'https://www.sota2.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  leo9-sota2:
    url: "https://www.sota2.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "leo9-sota2": {
      "Transport": "http",
      "Url": "https://www.sota2.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add leo9-sota2 -t streamable-http -u 'https://www.sota2.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "leo9-sota2": {
      "type": "http",
      "url": "https://www.sota2.com/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.

### 2026-11-01 (score 68, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_ai_solutions” rewrote its description, which is the text the model reads
- [security] Tool “search_companies” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 399 → 314
- [functional] Server version: 2.5.1 → 2.6.1
- [functional] New tool “find_ai_companies”
- [cosmetic] Tool “find_ai_solutions” changed its title: Compare AI solutions by industry and task → Read AI product comparisons by task
- [cosmetic] Tool “search_companies” changed its title: Find AI companies for a business problem → Look up an AI company by name

### 2026-10-31 (score 67, 0)

- [security regression] Stability: 0.03 → fail
- [security regression] Tool “get_company_leaderboard” was removed
- [security regression] Tool “get_research_benchmark” was removed
- [security regression] Tool “get_research_entity” was removed
- [security regression] Tool “list_company_leaderboards” was removed
- [security regression] Tool “list_research_domains” was removed
- [security regression] Tool “search_research” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_company” rewrote its description, which is the text the model reads
- [security] Tool “get_solution_rankings” rewrote its description, which is the text the model reads
- [security] Tool “search_companies” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 231 → 399
- [functional improvement] Tool coverage: 50% → 77%
- [functional] Server version: 1.0.6 → 2.5.1
- [functional] New tool “find_ai_solutions”
- [cosmetic] “search_companies” added an optional parameter “intent”
- [cosmetic] “get_company” reworded the description of “dimensions”
- [cosmetic] “search_companies” reworded the description of “query”
- [cosmetic] Tool “get_company” changed its title: Get company facts and products → Read AI company products and evidence
- [cosmetic] Tool “search_companies” changed its title: Find AI companies → Find AI companies for a business problem

### 2026-10-30 (score 67, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-29 (score 67)

First indexed and scored.

## MCP tools (7)

### `find_ai_companies` (~221 tokens)

Find and compare AI companies

Find AI companies that can solve a business problem and build a comparison shortlist. Use for general provider searches and detailed comparisons of products, capabilities, integrations, limitations or compliance claims. Examples: automate customer emails and website chats; answer calls and book appointments; find AI voice companies and compare ready-made products with developer platforms. Pass the full English workflow, channels, industry and constraints. Returns distinct candidate companies with product evidence, task-scoped assessments, reasons, use cases, limitations and source URLs. Read get_company for comparable company/product facts. Cite the returned SOTA2 pages for data used in the answer. Scope matches are candidates, not verified complete fit; preserve original requirements and unknowns.

Input parameters:

- `limit` (integer): Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.
- `query` (string, required): Full English business problem, requested work, channels, industry and constraints. Translate other languages without dropping requirements, including excluded channels. A known company name is not ne…

Output parameters:

- `data` (object)

### `find_ai_solutions` (~263 tokens)

Read AI product comparisons by task

Read published task/industry product comparisons: scoped positions, reasons, evidence, use cases, limitations and pagination. For a company shortlist or a detailed vendor comparison, start with find_ai_companies, then get_company for company/product facts. This tool accepts an English business problem or task and an optional industry; each scope previews up to three products with company IDs and follow-up calls. Positions belong to their scope. Preserve the requested industry and constraints, verify complete product fit, and keep missing coverage explicit.

Input parameters:

- `industry` (string): Optional requested industry ID, slug or English name, e.g. healthcare, finance or logistics. Recognizable industries in the query are also retained; conflicting or multiple industries require selecti…
- `limit` (integer): Number of matching leaderboard scopes (1–5), each previewing up to three products. These scopes do not form a combined ranking.
- `offset` (integer): Row offset. Use nextOffset from the previous response.
- `query` (string, required): English business problem, workflow or task, e.g. 'companies that can automate customer support emails and live chat' or 'vendors that answer phone calls and book appointments'. Translate non-English…

Output parameters:

- `data` (object)

### `search_companies` (~240 tokens)

Look up an AI company by name

Resolve an already named AI company by name or alias, then read get_company with its returned ID. The default company_name mode also accepts concise literal capability keywords for broader unranked candidates; such matches do not prove industry fit. For a business problem or a new vendor shortlist, use find_ai_companies. Existing callers can still use intent business_need here with a full English workflow; it returns the same task-scoped company candidates as find_ai_companies. Preserve coverage gaps and unknown facts.

Input parameters:

- `intent` (string): Use business_need for a full English problem/workflow when finding new providers. company_name preserves existing exact-name/alias or concise literal capability-keyword lookup.
- `limit` (integer): Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.
- `query` (string, required): With business_need: the full English problem, desired work, industry and constraints, preserving all channels and phone/booking requirements. Translate other languages without dropping requirements.…

Output parameters:

- `data` (object)

### `get_company` (~283 tokens)

Read AI company products and evidence

Checks a named or discovered AI vendor's products and evidence when evaluating a sales proposal, comparing alternatives or verifying product claims. Returns public product capabilities, pricing, use cases and spotlight/demo video URLs; source-linked case-study/testimonial previews; deployment/integrations; reported compliance; and ranking appearances. Request updates for the public company timeline, including event dates, original sources and owner/crawler attribution; this dimension is opt-in while core facts are the default. Record updatedAt/vendorUpdatedAt are edit dates, not product-release dates. Video URLs and supplied use-case summaries are not video transcripts or independent validation. Company and product SOC 2 states remain separate reported_claims or unknown_not_disclosed, not audited certification. Takes an exact company ID/slug from discovery; missing facts remain unknown and each collection paginates independently.

Input parameters:

- `company` (string, required): Exact returned company ID or slug.
- `dimensions` (array): products includes use cases, spotlight/demo video metadata and record-edit dates; customers includes public case-study/testimonial previews; updates explicitly fetches the public dated timeline. Othe…
- `limit` (integer): Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.
- `offset` (integer): Row offset. Use nextOffset from the previous response.

Output parameters:

- `data` (object)

### `list_industries` (~112 tokens)

Map industries to IDs

Lists supported industries with canonical IDs/slugs, names, descriptions and aliases. Includes cross-industry, consumer and agent audiences when available. An optional query filters this directory; without it the directory is browsable with pagination.

Input parameters:

- `limit` (integer): Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.
- `offset` (integer): Row offset. Use nextOffset from the previous response.
- `query` (string)

Output parameters:

- `data` (object)

### `list_tasks` (~152 tokens)

Map AI tasks to IDs

Lists AI solution task IDs, slugs, descriptions and company coverage, optionally within an industry. An optional query filters the directory. Ambiguous 'AI verification platform', 'verification' and 'verify' queries include clarification_required with identities/KYC, document authenticity and factual-claim choices; these have no selected meaning. Company coverage overlaps across tasks, so task counts are not additive distinct-company totals.

Input parameters:

- `industry` (string)
- `limit` (integer): Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.
- `offset` (integer): Row offset. Use nextOffset from the previous response.
- `query` (string)

Output parameters:

- `data` (object)

### `get_solution_rankings` (~189 tokens)

Get AI solution rankings

Compares AI software for a known industry/task using published positions, reasons, best use cases, evidence and caveats. Use a scope from find_ai_solutions or industry/task discovery, including follow-ups such as why a product ranks first or the next page. Industry only returns a task directory; industry + task selects that exact scope; task only selects cross-industry. Missing combinations return not_found with guidance, never substitute rankings. Positions/scores are scoped, not comparable across scopes; unreviewed positions/scores are null. Top N corresponds to limit N rows.

Input parameters:

- `industry` (string)
- `limit` (integer): Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.
- `offset` (integer): Row offset. Use nextOffset from the previous response.
- `task` (string)

Output parameters:

- `data` (object)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/leo9-sota2/www#diagnostics

## Score history

- 2026-11-05: 68
- 2026-11-04: 68
- 2026-11-03: 68
- 2026-11-02: 68
- 2026-11-01: 68
- 2026-10-31: 67
- 2026-10-30: 67
- 2026-10-29: 67

## Common questions

### What is the SOTA2 — AI Solution Rankings MCP server?

SOTA2 — AI Solution Rankings is an MCP server listed in the public MCP registry as io.github.leo9/sota2. Compare published AI solution rankings, company facts and research benchmarks with sources. This page covers its hosted endpoint (https://www.sota2.com/mcp).

### Is the SOTA2 — AI Solution Rankings MCP server safe to use?

SOTA2 — AI Solution Rankings scores 68 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 SOTA2 — AI Solution Rankings MCP server expose?

SOTA2 — AI Solution Rankings exposes 7 tools: find_ai_companies, find_ai_solutions, search_companies, get_company, list_industries, and 2 more. Their descriptions and schemas cost roughly 1,460 tokens of context every time the server is loaded.

### Does the SOTA2 — AI Solution Rankings MCP server require authentication?

No. We connected to SOTA2 — AI Solution Rankings without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the SOTA2 — AI Solution Rankings MCP server still maintained?

SOTA2 — AI Solution Rankings 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://www.sota2.com/mcp
- Website: https://www.sota2.com/with-ai
- Changelog RSS feed: https://verifymcp.io/servers/leo9-sota2/www.xml
- Changelog JSON feed: https://verifymcp.io/servers/leo9-sota2/www.json
- HTML version of this page: https://verifymcp.io/servers/leo9-sota2/www