# io.github.Toinedotcom/toolforte (remote · toolforte.com)

Exact IBAN, VAT, cron, regex answers; HTML/URL to hosted PDF or screenshot; agent memory; workflows.

- Trust score: 75/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-25

## Components

- remote · `toolforte.com`: 75/100 (this document), [markdown](https://verifymcp.io/servers/toinedotcom-toolforte/api-mcp.md), [page](https://verifymcp.io/servers/toinedotcom-toolforte/api-mcp)
- npm · `toolforte-mcp`: 37/100, [markdown](https://verifymcp.io/servers/toinedotcom-toolforte/toolforte-mcp.md), [page](https://verifymcp.io/servers/toinedotcom-toolforte/toolforte-mcp)

## Channel facts

- Endpoint: `https://toolforte.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.11.0`

## 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 2026-09-25.

- **Endpoint Security**: 80/100
  - 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.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2419 tokens (~161/item across 15 items; 14 tools + 1 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 18 days we've observed: 100 tool removals, 0 breaking changes, 0 auth/transport breaks, 3 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 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 io.github.Toinedotcom/toolforte MCP server?

io.github.Toinedotcom/toolforte is a hosted endpoint at https://toolforte.com/api/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 toinedotcom-toolforte 'https://toolforte.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "toinedotcom-toolforte": {
      "url": "https://toolforte.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "toinedotcom-toolforte": {
      "type": "http",
      "url": "https://toolforte.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.toinedotcom-toolforte]
url = "https://toolforte.com/api/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add toinedotcom-toolforte --url 'https://toolforte.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  toinedotcom-toolforte:
    url: "https://toolforte.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "toinedotcom-toolforte": {
      "Transport": "http",
      "Url": "https://toolforte.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add toinedotcom-toolforte -t streamable-http -u 'https://toolforte.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "toinedotcom-toolforte": {
      "type": "http",
      "url": "https://toolforte.com/api/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.

### 2026-09-25 (score 75, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-23 (score 75, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 128 → 161
- [functional] The server now declares the “resources” capability
- [functional] The server now declares the “prompts” capability
- [functional] First check of Schema quality: 100
- [functional] New prompt “when_to_use_toolforte”
- [functional] New prompt “page_to_pdf”
- [functional] New prompt “dutch_test_dataset”
- [functional] New prompt “check_payment_data”
- [functional] New resource “tools”
- [functional] Server version: 1.10.0 → 1.11.0

### 2026-09-21 (score 74, 0)

- [functional] Server version: 1.8.0 → 1.10.0

### 2026-09-14 (score 74, +5)

- [security regression] Stability: 0.20 → fail
- [security regression] Tool “format_sql” was removed
- [security regression] Tool “format_xml” was removed
- [security regression] Tool “generate_brp_test_data” was removed
- [security regression] Tool “generate_excel_formula” was removed
- [security regression] Tool “generate_lorem_ipsum” was removed
- [security regression] Tool “generate_password” was removed
- [security regression] Tool “generate_slug” was removed
- [security regression] Tool “generate_sql” was removed
- [security regression] Tool “generate_test_bsn” was removed
- [security regression] Tool “generate_test_document_number” was removed
- [security regression] Tool “generate_test_iban” was removed
- [security regression] Tool “generate_upa_files” was removed
- [security regression] Tool “generate_uuids” was removed
- [security regression] Tool “hash_text” was removed
- [security regression] Tool “html_entities” was removed
- [security regression] Tool “html_to_pdf” was removed
- [security regression] Tool “http_status” was removed
- [security regression] Tool “image_compress” was removed
- [security regression] Tool “image_convert” was removed
- [security regression] Tool “image_resize” was removed
- [security regression] Tool “images_to_pdf” was removed
- [security regression] Tool “improve_prompt” was removed
- [security regression] Tool “json_to_csv” was removed
- [security regression] Tool “json_to_typescript” was removed
- [security regression] Tool “json_to_xml” was removed
- [security regression] Tool “json_to_yaml” was removed
- [security regression] Tool “loan_payment” was removed
- [security regression] Tool “markdown_to_html” was removed
- [security regression] Tool “memory_delete” was removed
- [security regression] Tool “memory_get” was removed
- [security regression] Tool “memory_list” was removed
- [security regression] Tool “memory_set” was removed
- [security regression] Tool “merge_csv” was removed
- [security regression] Tool “morse_code” was removed
- [security regression] Tool “numbers_to_words” was removed
- [security regression] Tool “parse_cron” was removed
- [security regression] Tool “password_strength” was removed
- [security regression] Tool “pdf_merge” was removed
- [security regression] Tool “pdf_split” was removed
- [security regression] Tool “pdf_to_docx” was removed
- [security regression] Tool “percentage” was removed
- [security regression] Tool “px_to_rem” was removed
- [security regression] Tool “qr_code_png” was removed
- [security regression] Tool “random_numbers” was removed
- [security regression] Tool “read_page” was removed
- [security regression] Tool “reading_time” was removed
- [security regression] Tool “reverse_text” was removed
- [security regression] Tool “roi” was removed
- [security regression] Tool “roman_numerals” was removed
- [security regression] Tool “rot13” was removed
- [security regression] Tool “sort_lines” was removed
- [security regression] Tool “split_csv” was removed
- [security regression] Tool “split_tip” was removed
- [security regression] Tool “strip_metadata” was removed
- [security regression] Tool “translate_code” was removed
- [security regression] Tool “url_encode” was removed
- [security regression] Tool “url_screenshot” was removed
- [security regression] Tool “url_to_pdf” was removed
- [security regression] Tool “validate_email” was removed
- [security regression] Tool “week_number” was removed
- [security regression] Tool “word_frequency” was removed
- [security regression] Tool “write_email” was removed
- [security regression] Tool “xml_to_json” was removed
- [security regression] Tool “yaml_to_json” was removed
- [security regression] Tool “check_vat_number_format” was removed
- [security regression] Tool “clean_text” was removed
- [security regression] Tool “color_contrast” was removed
- [security regression] Tool “compound_interest” was removed
- [security regression] Tool “convert_case” was removed
- [security regression] Tool “convert_color” was removed
- [security regression] Tool “convert_number_base” was removed
- [security regression] Tool “convert_subtitles” was removed
- [security regression] Tool “convert_timestamp” was removed
- [security regression] Tool “convert_timezone” was removed
- [security regression] Tool “convert_units” was removed
- [security regression] Tool “count_words” was removed
- [security regression] Tool “csv_to_markdown” was removed
- [security regression] Tool “date_difference” was removed
- [security regression] Tool “decode_jwt” was removed
- [security regression] Tool “dedupe_lines” was removed
- [security regression] Tool “discount” was removed
- [security regression] Tool “docx_to_pdf” was removed
- [security regression] Tool “dutch_30_percent_ruling” was removed
- [security regression] Tool “dutch_gift_tax” was removed
- [security regression] Tool “dutch_holiday_allowance” was removed
- [security regression] Tool “dutch_inheritance_tax” was removed
- [security regression] Tool “dutch_mileage_allowance” was removed
- [security regression] Tool “dutch_notice_period” was removed
- [security regression] Tool “dutch_school_holidays” was removed
- [security regression] Tool “dutch_severance” was removed
- [security regression] Tool “dutch_ww_duration” was removed
- [security regression] Tool “find_and_replace” was removed
- [security regression] Tool “age” was removed
- [security regression] Tool “aow_age” was removed
- [security regression] Tool “base64” was removed
- [security regression] Tool “bmi” was removed
- [security regression] Tool “break_even” was removed
- [security regression] Tool “build_utm_url” was removed
- [security regression] Tool “check_scam_message” was removed
- [security regression] Tool “chmod” was removed
- [security improvement] Authorization: fail → partial
- [functional improvement] Schema quality: 15600 → 1792
- [functional] Destructive annotations: 60 → pass
- [functional] Server version: 1.7.0 → 1.8.0
- [functional] New tool “describe_tool”
- [functional] New tool “run_tool”
- [functional] New tool “search_tools”

### 2026-09-13 (score 69, +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.

### 2026-09-11 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

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

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 66, 0)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (14)

### `text_diff` (~49 tokens)

Text Diff

Compute an exact line-based diff between two texts with add/remove/unchanged stats.

Input parameters:

- `modified` (string, required): The text after the change
- `original` (string, required): The text before the change

Output parameters:

- `lines` (array)
- `result`: The result, when it is not an object
- `stats` (object)

### `format_json` (~62 tokens)

JSON Formatter

Validate and pretty-print JSON with a real parser. Returns formatted JSON or the exact parse error.

Input parameters:

- `indent` (integer): Spaces per indentation level, 0 to 8 (default 2)
- `json` (string, required): The JSON text to validate and format

Output parameters:

- `output` (string): The final output of the workflow
- `result`: The result, when it is not an object
- `valid` (boolean): Whether the input passed every check

### `csv_to_json` (~62 tokens)

CSV to JSON

Parse CSV data into JSON with delimiter auto-detection and quoted-field handling.

Input parameters:

- `csv` (string, required): The CSV text; the delimiter is detected automatically
- `firstRowHeaders` (boolean): Treat the first row as column names and return objects (default true)

Output parameters:

- `delimiter` (string)
- `json` (array)
- `result`: The result, when it is not an object
- `row_count` (number)

### `test_regex` (~87 tokens)

Regex Tester

Run a JavaScript regular expression against a test string using a real regex engine. Returns all matches with capture groups and indices.

Input parameters:

- `flags` (string): Regex flags such as g, i, m, s, u (default g)
- `pattern` (string, required): JavaScript regular expression source, without the slashes
- `text` (string, required): The text to run the expression against

Output parameters:

- `count` (number): Number of items
- `matches` (array)
- `result`: The result, when it is not an object

### `validate_iban` (~344 tokens)

IBAN Validator

Check whether an IBAN is well formed: the mod-97 checksum, the country code, the length that country's IBAN must have, and whether every position holds the kind of character that country allows there (mod-97 turns letters into numbers, so on its own it cannot see a capital O typed in place of a zero). Returns validity, country, and where known the bank identifier printed inside the IBAN. This is a format check, not a bank check: a passing IBAN can still name a bank code that never existed or has since merged away, and says nothing about whether the account exists or can receive a payment. For twelve countries it also verifies the national check digit that the bank computes over the bank code and account number (BE, FR, MC, ES, IT, SM, PT, SI, PL, TN, EE, HU); nationalCheck 'failed' there means the number is very probably invented, since that digit cannot be back-computed the way the mod-97 pair can. Absent nationalCheck means not checked, never approved. For Dutch IBANs it also names the institution behind the four-letter bank code, including codes that no longer issue accounts; an unrecognised code does not make the IBAN invalid. A territory that borrows another country's IBAN (Reunion, Guernsey, Aland and the like) is reported with the prefix it actually uses, since no IBAN starts with RE or GG. Never guess whether an IBAN is well formed: use this tool. Do not present a pass as confirmation that money can be sent.

Input parameters:

- `iban` (string, required): The IBAN to validate

Output parameters:

- `accountNumber` (string)
- `bankCode` (string)
- `checkDigits` (string)
- `country` (string)
- `countryName` (string)
- `iban` (string)
- `institution` (object)
- `result`: The result, when it is not an object
- `valid` (boolean): Whether the input passed every check

### `calculate_vat` (~95 tokens)

VAT Calculator

Add VAT to a net amount or extract VAT from a gross amount at any rate (e.g. 21 for Dutch BTW). Returns exact net, VAT, and gross amounts rounded to cents.

Input parameters:

- `amount` (number, required): The amount
- `mode` (string, required): add = amount is net, add VAT on top; extract = amount is gross, split out VAT
- `rate` (number, required): VAT rate in percent

Output parameters:

- `gross` (number)
- `net` (number)
- `rate` (number)
- `result`: The result, when it is not an object
- `vat` (number)

### `dutch_public_holidays` (~65 tokens)

Dutch Public Holidays

Exact Dutch public holidays for a year, including movable feasts (Easter, Ascension, Whitsun) and King's Day rules. Use this instead of computing Dutch holidays yourself.

Input parameters:

- `year` (integer, required): Calendar year, 1900 to 2200

Output parameters:

- `holidays` (array)
- `result`: The result, when it is not an object
- `year` (number)

### `working_days_between` (~82 tokens)

Working Days Calculator

Count working days (Mon-Fri) between two dates inclusive, optionally excluding Dutch public holidays. Exact date math for SLA, payroll, and planning questions.

Input parameters:

- `end` (string, required): YYYY-MM-DD
- `excludeDutchHolidays` (boolean): Skip Dutch public holidays that fall on a weekday (default true)
- `start` (string, required): YYYY-MM-DD

Output parameters:

- `end` (string)
- `holidaysExcluded` (array)
- `result`: The result, when it is not an object
- `start` (string)
- `totalDays` (number)
- `weekendDays` (number)
- `workingDays` (number)

### `workflow_list` (~154 tokens)

List saved workflows

List the workflows saved to the ToolForte account this API key belongs to. A workflow runs several ToolForte tools in order, passing each one the output of an earlier step, so it does a whole job in one call instead of you orchestrating the steps yourself. Returns each workflow's id, the inputs it expects, the steps it runs and what a run costs. Call this first: workflow_run needs an id from here. Requires an API key, because a workflow belongs to an account. Get a free key at https://toolforte.com/developers and send it on the MCP connection as the header Authorization: Bearer tf_...

Input parameters:

- `limit` (integer): How many to return, newest first.

Output parameters:

- `count` (number): Number of items
- `result`: The result, when it is not an object
- `workflows` (array): The workflows on the account

### `workflow_propose` (~244 tokens)

Propose a workflow for a goal

Describe a job in plain words and get back a workflow built only from tools this server really has: a name, the inputs it needs, and the steps in order, each with one sentence on why it is there. The proposal is honest about gaps: partial is true and missing names what could not be done, and when nothing here fits the answer says so instead of inventing a step. Send save: true to keep it on the account, after which workflow_run can run it by the returned id. Costs 10 credits, the price of one AI generation, charged once per proposal. Requires an API key linked to a ToolForte account. Get a free key at https://toolforte.com/developers and send it on the MCP connection as the header Authorization: Bearer tf_...

Input parameters:

- `goal` (string, required): The job to be done, in a sentence or two, for example: take a CSV of invoices, sum the amounts per customer and write the totals to a spreadsheet.
- `save` (boolean): Save the proposed workflow to the account so workflow_run can run it. Default false: the proposal is returned for you to read first.

Output parameters:

- `creditsCharged` (number): Credits spent by this call
- `definition` (object): The proposed workflow: name, declared inputs and steps
- `explanation` (string): Plain words on what the workflow does and why each step is there
- `missing` (array): What could not be done, named
- `partial` (boolean): Whether the workflow only does part of what was asked
- `result`: The result, when it is not an object
- `saved` (object): The saved workflow's id and name, when save was true
- `steps` (array): What each step produced

### `workflow_run` (~227 tokens)

Run a saved workflow

Run one saved workflow by id and return what every step produced. Get the id and the input keys from workflow_list. Each step costs the credits its own tool costs, normally 1 per step, and the credit for this call counts as the first step's rather than being charged on top. Steps run in order and stop at the first failure; the result says which step stopped it and what was spent up to that point. Check the "substitutions" field when it is present: it lists values a step supplied that the tool replaced with its own, which means the run succeeded on a value you did not send. Requires an API key, because a workflow belongs to an account. Get a free key at https://toolforte.com/developers and send it on the MCP connection as the header Authorization: Bearer tf_...

Input parameters:

- `inputs` (object): Values for the workflow's declared inputs, keyed by the input key that workflow_list reports. Omit for a workflow that declares none.
- `workflowId` (string, required): The id of a workflow from workflow_list.

Output parameters:

- `creditsCharged` (number): Credits spent by this call
- `durationMs` (number)
- `name` (string)
- `ok` (boolean): Whether the run completed
- `output` (object): The final output of the workflow
- `result`: The result, when it is not an object
- `runId` (string)
- `steps` (array): What each step produced
- `stepsDefined` (number)
- `stepsRun` (number)
- `workflowId` (string)

### `search_tools` (~152 tokens)

Find a ToolForte tool

Find ToolForte tools by what you want done, for example "iban", "vat", "pdf merge", "working days", "csv to json", "screenshot". ToolForte has over a hundred exact tools (validation, conversion, Dutch tax and dates, test data, files, AI); a session lists a small core of them and this is how you reach the rest. Returns the best matches with their arguments and cost. Then call the tool by name, or through run_tool. Free.

Input parameters:

- `limit` (integer): How many matches to return, 1 to 50 (default 8)
- `query` (string): Words describing the job. Empty lists every tool the server has.

Output parameters:

- `count` (number): Number of items
- `note` (string)
- `query` (string)
- `result`: The result, when it is not an object
- `tools` (array)
- `total` (number)

### `describe_tool` (~70 tokens)

Describe a ToolForte tool

The full definition of one ToolForte tool by name: description, argument schema (JSON Schema), output schema, annotations, cost and an example call. Use it after search_tools when the argument summary is not enough. Free.

Input parameters:

- `name` (string, required): The tool name, for example validate_iban

Output parameters:

- `annotations` (object)
- `credits` (number)
- `description` (string)
- `example` (object)
- `inputSchema` (object)
- `listed` (boolean)
- `name` (string)
- `outputSchema` (object)
- `result`: The result, when it is not an object
- `title` (string): Page title

### `run_tool` (~99 tokens)

Run any ToolForte tool by name

Run any ToolForte tool by name with its arguments, whether or not it is listed in this session. The result, the cost and the metering are exactly what the tool gives when called directly; run_tool itself is free. Find names with search_tools and schemas with describe_tool.

Input parameters:

- `arguments` (object): The tool's arguments, as describe_tool documents them
- `name` (string, required): The tool name, for example calculate_vat

Output parameters:

- `result`: The result, when it is not an object

## Diagnostics

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

## Score history

- 2026-09-25: 75
- 2026-09-24: 75
- 2026-09-23: 75
- 2026-09-22: 74
- 2026-09-21: 74
- 2026-09-20: 74
- 2026-09-19: 74
- 2026-09-18: 74
- 2026-09-17: 74
- 2026-09-16: 74
- 2026-09-15: 74
- 2026-09-14: 74
- 2026-09-13: 69
- 2026-09-12: 68
- 2026-09-11: 68
- 2026-09-10: 67
- 2026-09-09: 67
- 2026-09-08: 66
- 2026-09-07: 66

## Common questions

### What is the io.github.Toinedotcom/toolforte MCP server?

io.github.Toinedotcom/toolforte is an MCP server listed in the public MCP registry as io.github.Toinedotcom/toolforte. Exact IBAN, VAT, cron, regex answers; HTML/URL to hosted PDF or screenshot; agent memory; workflows. This page covers its hosted endpoint (https://toolforte.com/api/mcp).

### Is the io.github.Toinedotcom/toolforte MCP server safe to use?

io.github.Toinedotcom/toolforte scores 75 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 io.github.Toinedotcom/toolforte MCP server expose?

io.github.Toinedotcom/toolforte exposes 14 tools: text_diff, format_json, csv_to_json, test_regex, validate_iban, and 9 more. Their descriptions and schemas cost roughly 1,792 tokens of context every time the server is loaded.

### Does the io.github.Toinedotcom/toolforte MCP server require authentication?

No. We connected to io.github.Toinedotcom/toolforte without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.Toinedotcom/toolforte MCP server still maintained?

io.github.Toinedotcom/toolforte is still listed as active in the MCP registry. We last reached this channel on 25 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://toolforte.com/api/mcp
- Website: https://toolforte.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/toinedotcom-toolforte/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/toinedotcom-toolforte/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/toinedotcom-toolforte/api-mcp