# vrsai (remote · api.vrsai.tech)

Machine-native capabilities with explicit contracts and machine-readable commerce.

- Trust score: 69/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `api.vrsai.tech`: 69/100 (this document), [markdown](https://verifymcp.io/servers/tech-vrsai-mcp/api.md), [page](https://verifymcp.io/servers/tech-vrsai-mcp/api)

## Channel facts

- Endpoint: `https://api.vrsai.tech/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-09-20.

- **Endpoint Security**: 49/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (openapi_agent_readiness).
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1340 tokens (~223/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 87/100
  - Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 78/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 24% 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the vrsai MCP server?

vrsai is a hosted endpoint at https://api.vrsai.tech/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 tech-vrsai-mcp 'https://api.vrsai.tech/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "tech-vrsai-mcp": {
      "url": "https://api.vrsai.tech/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tech-vrsai-mcp": {
      "type": "http",
      "url": "https://api.vrsai.tech/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.tech-vrsai-mcp]
url = "https://api.vrsai.tech/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tech-vrsai-mcp": {
      "type": "remote",
      "url": "https://api.vrsai.tech/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tech-vrsai-mcp --url 'https://api.vrsai.tech/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  tech-vrsai-mcp:
    url: "https://api.vrsai.tech/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "tech-vrsai-mcp": {
      "Transport": "http",
      "Url": "https://api.vrsai.tech/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add tech-vrsai-mcp -t streamable-http -u 'https://api.vrsai.tech/mcp'
```

### Other

```json
{
  "mcpServers": {
    "tech-vrsai-mcp": {
      "type": "http",
      "url": "https://api.vrsai.tech/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.

### 2026-09-20 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-05 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (6)

### `openapi_agent_readiness` (~193 tokens)

OpenAPI Agent Readiness

Call before integrating an OpenAPI-described API with autonomous agents to determine whether the contract is machine-actionable. Deterministically analyzes a self-contained OpenAPI 3.0, 3.1, or 3.2 description and returns a readiness score, verdict, and actionable findings covering operation semantics, request and response contracts, authentication clarity, reference integrity, and machine usability. It does not apply when generating a new OpenAPI description from source code. Paid invocation: 30000 micro-USD per successful execution.

Input parameters:

- `document` (object, required): The OpenAPI description as a parsed JSON object (not a YAML/JSON string). Must include a top-level 'openapi' version field of family 3.0, 3.1, or 3.2. Only inline schemas and local references ('#/...…

Output parameters:

- `dimensions` (array)
- `findings` (array)
- `openapi_version` (string): The detected 'openapi' version string, or 'unknown' if it could not be determined.
- `ruleset_version` (string): Version of the finding codes, dimension weights, and scoring thresholds that produced this result — independent of the capability's own contract version. See RULESET_VERSION in rules.ts.
- `score` (integer)
- `summary` (object)
- `verdict`: ready: score >= 85 and no blocking finding. needs_changes: score >= 60 and no blocking finding. not_ready: score < 60, or at least one blocking finding regardless of score.

### `sql_preflight` (~255 tokens)

SQL Preflight

Call this immediately before an autonomous agent, coding assistant, or automated pipeline executes PostgreSQL write, DDL, or administrative SQL against a production-capable connection. It parses the complete statement set with a real PostgreSQL AST parser and prevents the costly mistake of an agent silently deleting, truncating, or dropping data it should not have touched. It detects unbounded DELETE and UPDATE (no WHERE clause), TRUNCATE, destructive DROP and CASCADE, mutation of caller-declared protected relations, and availability-sensitive DDL such as a non-concurrent CREATE INDEX or hazardous ALTER TABLE change. It returns a deterministic PROCEED, REVIEW, or BLOCK decision with stable reason codes, a per-statement inventory, and an explicit coverage report of exactly what was and was not assessed — parse failure and unparseable or unmodeled syntax always fail closed to REVIEW, never PROCEED. PostgreSQL is the only supported dialect in this version. It does not apply when executing SQL or connecting to a database. Paid invocation: 50000 micro-USD per successful execution.

Input parameters:

- `context` (object)
- `policy` (object)
- `sql` (string, required): A complete PostgreSQL statement or semicolon-separated statement list.

Output parameters:

- `checks` (array)
- `coverage` (object)
- `decision`
- `input_fingerprint` (string): SHA-256 fingerprint ("v1:<hex>") of the exact submitted {sql, context, policy} tuple. Identical input and policy always produce the identical fingerprint, independent of commercial/payment mode. See…
- `machine_action`
- `reason_codes` (array)
- `ruleset_version` (string): Version of the reason-code catalog and policy defaults that produced this result, independent of the capability's own contract version. See RULESET_VERSION in rules.ts.
- `statement_count` (integer)
- `statements` (array)

### `invoice_match` (~252 tokens)

Invoice Match

Call after invoice extraction and immediately before an accounts-payable or procurement agent approves a purchase-order-backed supplier invoice. Invoice Match performs deterministic three-way matching across invoice lines, one or more purchase orders, cumulative goods-receipt evidence, prior invoicing, price tolerances, quantities, units, and exact invoice arithmetic. Cumulative invoicing (prior plus current) is always compared against cumulative receipts and against the ordered quantity, so repeated partial invoices against partial deliveries cannot silently overbill. It returns PROCEED, REVIEW, or BLOCK with line-level discrepancy codes and evidence, and always discloses which checks were and were not performed. Use it for invoice matching, PO matching, 3-way matching, goods-receipt matching, overbilling prevention, and autonomous AP approval controls. It does not OCR documents, infer product matches, retrieve ERP data, determine tax, or execute payment. Paid invocation: 50000 micro-USD per successful execution.

Input parameters:

- `evidence` (object, required)
- `invoice` (object, required)
- `match_mode` (string, required)
- `policy` (object)
- `purchase_orders` (array, required)
- `receipts` (array, required)
- `recent_invoices` (array)

Output parameters:

- `checks` (array)
- `coverage` (object)
- `decision`
- `input_fingerprint` (string): SHA-256 fingerprint ("v1:<hex>") of the exact submitted evaluation input tuple. Identical input and policy always produce the identical fingerprint. See fingerprint.ts.
- `invoice` (object)
- `line_results` (array)
- `machine_action`
- `reason_codes` (array)
- `ruleset_version` (string): Version of the reason-code catalog and policy defaults that produced this result, independent of the capability's own contract version. See RULESET_VERSION in rules.ts.
- `totals` (object)

### `payout_preflight` (~215 tokens)

Payout Preflight

Call immediately before an AI agent, accounts-payable system, treasury workflow, marketplace, or autonomous payment service authorizes or submits an outbound payout. Payout Preflight deterministically compares the candidate payout with caller-supplied trusted payment instructions, exact amount/currency policy, and supplied payout history; validates supported IBAN, US routing, and EVM destination structure; and detects destination changes, duplicate payouts, reused references, and first-seen destinations when history is complete. It returns PROCEED, REVIEW, or BLOCK with machine-readable evidence. Use it for payout validation, payment pre-validation, beneficiary-bank-detail change controls, duplicate-payment prevention, treasury controls, and agent payment guardrails. It does not verify bank-account ownership, perform Verification of Payee, AML/sanctions screening, submit payments, or guarantee settlement. Paid invocation: 50000 micro-USD per successful execution.

Input parameters:

- `history` (object)
- `payout` (object, required)
- `policy` (object)
- `trusted_baseline`

Output parameters:

- `candidate` (object)
- `checks` (array)
- `coverage` (object)
- `decision`
- `machine_action`
- `reason_codes` (array)
- `ruleset_version` (string)

### `decision_optimization` (~196 tokens)

Decision Optimization

Call immediately before an autonomous system must choose among multiple feasible actions under limited resources, costs, capacities, eligibility rules, and an economic objective. Decision Optimization compiles a typed economic problem — supplier/inventory allocation across sources and demands, task-to-resource assignment, budget-constrained option selection, or production/resource mix — into a bounded MILP model, solves it with a fixed deterministic solver profile, and independently re-verifies the candidate decision against the original problem before returning it. Returns OPTIMAL, FEASIBLE, INFEASIBLE, UNBOUNDED, or NO_SOLUTION with machine-readable evidence: verified feasibility, solver optimality/gap, binding constraints, and stable fingerprints. It does not perform vehicle routing, scheduling, calendar planning, 3D/carton packing, arbitrary LP/MIP solving, natural-language optimization modeling, forecasting, or external data retrieval. Paid invocation: 30000 micro-USD per successful execution.

Output parameters:

- `decision`
- `diagnostics` (object)
- `economics` (object)
- `evidence` (object)
- `machine_action`
- `problem_type`
- `quality` (object)
- `status`

### `package_install_preflight` (~229 tokens)

Package Install Preflight

Call immediately before installing or adding an exact third-party npm or PyPI package version. Checks current registry, known vulnerability/malicious-package, publisher withdrawal/deprecation, and verified provenance evidence and returns ALLOW, REVIEW, BLOCK, or UNKNOWN with machine-readable reasons. It accepts only an ECMA-427 Package URL with one exact published version; ranges, dist-tags, Git dependencies, archives, local packages, container images, other ecosystems, dependency graphs, repositories, SBOMs, and source-code or malware analysis are outside this version. It does not install, download, extract, clone, execute, or recommend a package version, and ALLOW never claims that a package is safe. Paid invocation: 10000 micro-USD per successful execution.

Input parameters:

- `expected_source_repository` (string): Optional HTTPS source repository identity to compare only with cryptographically verified deps.dev provenance. This URL is never fetched.
- `purl` (string, required): ECMA-427 Package URL for one exact published npm or PyPI version. Ranges, dist-tags, qualifiers, and subpaths are not supported.

Output parameters:

- `decision`
- `evidence` (array)
- `input_fingerprint` (string)
- `observations` (object)
- `observed_at` (string)
- `package` (object)
- `policy_version` (string)
- `reason_codes` (array)
- `unknowns` (array)

## Diagnostics

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

## Score history

- 2026-09-20: 69
- 2026-09-19: 68
- 2026-09-18: 68
- 2026-09-17: 68
- 2026-09-16: 67
- 2026-09-15: 67
- 2026-09-14: 66
- 2026-09-13: 66
- 2026-09-12: 65
- 2026-09-11: 65
- 2026-09-10: 64
- 2026-09-09: 64
- 2026-09-08: 63
- 2026-09-07: 63
- 2026-09-06: 62
- 2026-09-05: 62
- 2026-09-04: 61
- 2026-09-03: 61
- 2026-09-02: 61
- 2026-09-01: 60
- 2026-08-31: 60
- 2026-08-30: 59
- 2026-08-29: 59
- 2026-08-28: 58
- 2026-08-27: 58
- 2026-08-26: 57
- 2026-08-25: 54

## Common questions

### What is the vrsai MCP server?

vrsai is an MCP server listed in the public MCP registry as tech.vrsai/mcp. Machine-native capabilities with explicit contracts and machine-readable commerce. This page covers its hosted endpoint (https://api.vrsai.tech/mcp).

### Is the vrsai MCP server safe to use?

vrsai scores 69 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 vrsai MCP server expose?

vrsai exposes 6 tools: openapi_agent_readiness, sql_preflight, invoice_match, payout_preflight, decision_optimization, package_install_preflight. Their descriptions and schemas cost roughly 1,340 tokens of context every time the server is loaded.

### Does the vrsai MCP server require authentication?

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

### Is the vrsai MCP server still maintained?

vrsai is still listed as active in the MCP registry. We last reached this channel on 20 September 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://api.vrsai.tech/mcp
- Website: https://vrsai.tech/
- Changelog RSS feed: https://verifymcp.io/servers/tech-vrsai-mcp/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/tech-vrsai-mcp/api.json
- HTML version of this page: https://verifymcp.io/servers/tech-vrsai-mcp/api