Read-only desk for buyers and assistants: offer, prices, fit check, readiness scan, intake draft.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Deterministic fit check with nine yes/no signals taken from the published article on when an FDE fits and when it does not. Returns one of: fits, start_with_mapping, not_clear_yet, wait, something_else_fits_better, each with the sentence from the site it is based on. It also says when another kind of supplier is the simpler choice. Ask the person; do not guess the signals.
All nine yes/no signals, each true or false. Ask the person; do not guess. Three or four of signs 1-4 give fits.
Language of the answer: en (English, default) or nl (Dutch).
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http forwardsmith https://forwardsmith.com/mcp
Deterministic fit check with nine yes/no signals taken from the published article on when an FDE fits and when it does not. Returns one of: fits, start_with_mapping, not_clear_yet, wait, something_else_fits_better, each with the sentence from the site it is based on. It also says when another kind of supplier is the simpler choice. Ask the person; do not guess the signals.
| Argument | Type | Description |
|---|---|---|
| lang | string | Language of the answer: en (English, default) or nl (Dutch). |
| signals* | object | All nine yes/no signals, each true or false. Ask the person; do not guess. Three or four of signs 1-4 give fits. |
{
"type": "object",
"required": [
"signals"
],
"properties": {
"lang": {
"enum": [
"en",
"nl"
],
"type": "string",
"default": "en",
"description": "Language of the answer: en (English, default) or nl (Dutch)."
},
"signals": {
"type": "object",
"required": [
"one_process_with_owner",
"knowledge_with_people",
"runs_in_own_environment",
"want_to_carry_on_yourselves",
"experts_and_access_available",
"sharp_specification",
"standard_product_covers_it",
"only_independent_benchmark",
"wants_to_buy_model_or_platform"
],
"properties": {
"sharp_specification": {
"type": "boolean",
"description": "You already know exactly what has to be built and how to test it. true leads to something_else_fits_better (build capacity is the simpler choice)."
},
"knowledge_with_people": {
"type": "boolean",
"description": "Sign 2: the knowledge (exceptions, rules of thumb, red lines) sits with your people, not on paper."
},
"one_process_with_owner": {
"type": "boolean",
"description": "Sign 1 of the article: there is one process with an owner who can say what a good result is and has the authority to decide."
},
"runs_in_own_environment": {
"type": "boolean",
"description": "Sign 3: it has to run in your own environment (own cloud, VPC or on-premises) and talk to your existing systems."
},
"only_independent_benchmark": {
"type": "boolean",
"description": "All you want is an independent benchmark of models or agents. true leads to something_else_fits_better."
},
"standard_product_covers_it": {
"type": "boolean",
"description": "Your process does not differ from anyone else's and a standard package exists for it. true leads to something_else_fits_better."
},
"want_to_carry_on_yourselves": {
"type": "boolean",
"description": "Sign 4: you want to carry on yourselves afterwards; code, configuration, tests and documentation have to be yours."
},
"experts_and_access_available": {
"type": "boolean",
"description": "The people who do the work and the systems it happens in can be made available to the engineer now. false leads to the verdict wait."
},
"wants_to_buy_model_or_platform": {
"type": "boolean",
"description": "You mainly want to buy a model or a platform; Forwardsmith does not resell those. true leads to something_else_fits_better."
}
},
"description": "All nine yes/no signals, each true or false. Ask the person; do not guess. Three or four of signs 1-4 give fits.",
"additionalProperties": false
}
},
"additionalProperties": false
}Adds up the published starting prices for a chosen path of one to three steps (mapping, sprint, fde). Returns the lines, the sum as a lower bound in EUR excl. VAT, what is not included and what is not published. No discounts, no new prices.
| Argument | Type | Description |
|---|---|---|
| lang | string | Language of the answer: en (English, default) or nl (Dutch). |
| path* | array | One to three different steps in the order you would take them: mapping (Information Flow Mapping Session), sprint (FDE Build Sprint), fde (FDE 30-60-90 engagement). |
{
"type": "object",
"required": [
"path"
],
"properties": {
"lang": {
"enum": [
"en",
"nl"
],
"type": "string",
"default": "en",
"description": "Language of the answer: en (English, default) or nl (Dutch)."
},
"path": {
"type": "array",
"items": {
"enum": [
"mapping",
"sprint",
"fde"
],
"type": "string"
},
"maxItems": 3,
"minItems": 1,
"description": "One to three different steps in the order you would take them: mapping (Information Flow Mapping Session), sprint (FDE Build Sprint), fde (FDE 30-60-90 engagement).",
"uniqueItems": true
}
},
"additionalProperties": false
}Returns how a forward-deployed engineer of Forwardsmith works: Map, Build, Hand over; the five stations of the method and its golden rule; the six kinds of work; the eight points that belong in a statement of work; what must be ready before the start; and the handover test.
| Argument | Type | Description |
|---|---|---|
| lang | string | Language of the answer: en (English, default) or nl (Dutch). |
{
"type": "object",
"properties": {
"lang": {
"enum": [
"en",
"nl"
],
"type": "string",
"default": "en",
"description": "Language of the answer: en (English, default) or nl (Dutch)."
}
},
"additionalProperties": false
}Returns the three ways to start with Forwardsmith (Information Flow Mapping Session, FDE Build Sprint, FDE 30-60-90 engagement) with duration, starting price as a number in EUR excl. VAT, what it delivers, what is not included, the ownership statement and a list of things the site does not publish, so you can say so instead of guessing. Prices are starting prices, not quotes. Please cite the URL.
| Argument | Type | Description |
|---|---|---|
| lang | string | Language of the answer: en (English, default) or nl (Dutch). |
{
"type": "object",
"properties": {
"lang": {
"enum": [
"en",
"nl"
],
"type": "string",
"default": "en",
"description": "Language of the answer: en (English, default) or nl (Dutch)."
}
},
"additionalProperties": false
}Turns what you learned into a ready-to-send intake request: a brief in ten numbered lines, a link that opens the intake form with the message already filled in, and (once delivery to the inbox is confirmed) an e-mail to [email protected]. It sends nothing and stores nothing: the person reads the text, adds name and work e-mail and sends it. Do not put names, e-mail addresses or phone numbers in any field; the tool refuses them.
| Argument | Type | Description |
|---|---|---|
| lang | string | Language of the answer: en (English, default) or nl (Dutch). |
| problem* | string | What goes wrong today (10-600 characters). Line 2 of the brief. |
| process* | string | Which process should work, in general words (10-600 characters). Line 1 of the brief. |
| systems | string | Systems the process runs in, for example ERP, CRM, DMS or ticketing (up to 300 characters). |
| why_now | string | Why this matters now (up to 300 characters). |
| red_lines | string | Red lines: what the system must never do (up to 400 characters). |
| owner_role | string | Role of the process owner, not a name (up to 120 characters). |
Runs the same six-question FDE Readiness Scan as the page on forwardsmith.com, with the same scoring. Returns the score, the recommended starting point with its starting price, what is already in place and what to prepare. Self-assessment.
| Argument | Type | Description |
|---|---|---|
| lang | string | Language of the answer: en (English, default) or nl (Dutch). |
| answers* | object | The six answers of the FDE Readiness Scan, one option id per question, all six required (the same questions as the scan page). |
{
"type": "object",
"required": [
"answers"
],
"properties": {
"lang": {
"enum": [
"en",
"nl"
],
"type": "string",
"default": "en",
"description": "Language of the answer: en (English, default) or nl (Dutch)."
},
"answers": {
"type": "object",
"required": [
"process",
"history",
"sensitivity",
"redlines",
"models",
"volume"
],
"properties": {
"models": {
"enum": [
"none",
"adhoc",
"pilot",
"production"
],
"type": "string",
"description": "How do you use AI models or tools in this process today?"
},
"volume": {
"enum": [
"lt100",
"100-1000",
"1000-10000",
"gt10000"
],
"type": "string",
"description": "What monthly volume do you want this process to handle?"
},
"history": {
"enum": [
"lt50",
"50-200",
"200-1000",
"gt1000",
"unknown"
],
"type": "string",
"description": "How many historical cases with a known outcome can you pull?"
},
"process": {
"enum": [
"service",
"cases",
"documents",
"sales",
"internal",
"undecided"
],
"type": "string",
"description": "Which process would you start with?"
},
"redlines": {
"enum": [
"written",
"tacit",
"none",
"unsure"
],
"type": "string",
"description": "Are there hard red-line rules the system must never break?"
},
"sensitivity": {
"enum": [
"low",
"medium",
"high-classified",
"high-unclear"
],
"type": "string",
"description": "How sensitive is the data in these cases?"
}
},
"description": "The six answers of the FDE Readiness Scan, one option id per question, all six required (the same questions as the scan page).",
"additionalProperties": false
}
},
"additionalProperties": false
}Takes one process as 2-20 steps and returns per step whether it is handled by code (MCP/API), by a model (and on which route) or by a person, whether a redaction gate comes first and whether human approval is needed. Fixed rule table from the published method; no model is called. A preview of what the Information Flow Mapping Session does with your team, not a design. Describe steps in general words; no personal data.
| Argument | Type | Description |
|---|---|---|
| lang | string | Language of the answer: en (English, default) or nl (Dutch). |
| steps* | array | The steps of the process in order, 2 to 20. Each step is routed to code, a model or a person. |
| process_name* | string | Short name of the process in general words (3-160 characters). No personal data. |
{
"type": "object",
"required": [
"process_name",
"steps"
],
"properties": {
"lang": {
"enum": [
"en",
"nl"
],
"type": "string",
"default": "en",
"description": "Language of the answer: en (English, default) or nl (Dutch)."
},
"steps": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"kind"
],
"properties": {
"kind": {
"enum": [
"fetch_record",
"calculate",
"write_record",
"notify",
"classify",
"extract",
"summarise",
"draft_text",
"judge_edge_case",
"decide"
],
"type": "string",
"description": "What the step does. Handled by code: fetch_record, calculate, write_record, notify. Handled by a model: classify, extract, summarise, draft_text (Route A candidate), judge_edge_case (Route B candidate). Handled by a person: decide."
},
"name": {
"type": "string",
"maxLength": 120,
"minLength": 2,
"description": "What happens in this step, in general words (2-120 characters). No personal data."
},
"personal_data": {
"type": "boolean",
"default": false,
"description": "true when the step handles personal data; for a model step a redaction gate then comes first. Default false."
},
"external_effect": {
"type": "boolean",
"default": false,
"description": "true when the step pays, rejects, books or sends something outside the organisation; a step not taken by a person then needs human approval. Default false."
}
},
"additionalProperties": false
},
"maxItems": 20,
"minItems": 2,
"description": "The steps of the process in order, 2 to 20. Each step is routed to code, a model or a person."
},
"process_name": {
"type": "string",
"maxLength": 160,
"minLength": 3,
"description": "Short name of the process in general words (3-160 characters). No personal data."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 19, 2026.
| environment | string | Where the solution has to run: own_cloud, vpc, on_premises or undecided (not decided yet). |
| scan_answers | object | Optional: the six readiness-scan answers, the same format as answers in run_readiness_scan. Adds the score and the recommended start as line 10 of the brief. |
| preferred_start | string | Preferred starting point: mapping, sprint, fde or unsure (default). |
| data_sensitivity | string | How sensitive the data is: low, medium, high-classified (high, classified per field) or high-unclear (high, not yet classified). |
| known_outcome_cases | string | How many historical cases with a known outcome can be pulled: lt50 (fewer than 50), 50-200, 200-1000, gt1000 (more than 1,000) or unknown. |
{
"type": "object",
"required": [
"process",
"problem"
],
"properties": {
"lang": {
"enum": [
"en",
"nl"
],
"type": "string",
"default": "en",
"description": "Language of the answer: en (English, default) or nl (Dutch)."
},
"problem": {
"type": "string",
"maxLength": 600,
"minLength": 10,
"description": "What goes wrong today (10-600 characters). Line 2 of the brief."
},
"process": {
"type": "string",
"maxLength": 600,
"minLength": 10,
"description": "Which process should work, in general words (10-600 characters). Line 1 of the brief."
},
"systems": {
"type": "string",
"maxLength": 300,
"description": "Systems the process runs in, for example ERP, CRM, DMS or ticketing (up to 300 characters)."
},
"why_now": {
"type": "string",
"maxLength": 300,
"description": "Why this matters now (up to 300 characters)."
},
"red_lines": {
"type": "string",
"maxLength": 400,
"description": "Red lines: what the system must never do (up to 400 characters)."
},
"owner_role": {
"type": "string",
"maxLength": 120,
"description": "Role of the process owner, not a name (up to 120 characters)."
},
"environment": {
"enum": [
"own_cloud",
"vpc",
"on_premises",
"undecided"
],
"type": "string",
"description": "Where the solution has to run: own_cloud, vpc, on_premises or undecided (not decided yet)."
},
"scan_answers": {
"type": "object",
"required": [
"process",
"history",
"sensitivity",
"redlines",
"models",
"volume"
],
"properties": {
"models": {
"enum": [
"none",
"adhoc",
"pilot",
"production"
],
"type": "string",
"description": "How do you use AI models or tools in this process today?"
},
"volume": {
"enum": [
"lt100",
"100-1000",
"1000-10000",
"gt10000"
],
"type": "string",
"description": "What monthly volume do you want this process to handle?"
},
"history": {
"enum": [
"lt50",
"50-200",
"200-1000",
"gt1000",
"unknown"
],
"type": "string",
"description": "How many historical cases with a known outcome can you pull?"
},
"process": {
"enum": [
"service",
"cases",
"documents",
"sales",
"internal",
"undecided"
],
"type": "string",
"description": "Which process would you start with?"
},
"redlines": {
"enum": [
"written",
"tacit",
"none",
"unsure"
],
"type": "string",
"description": "Are there hard red-line rules the system must never break?"
},
"sensitivity": {
"enum": [
"low",
"medium",
"high-classified",
"high-unclear"
],
"type": "string",
"description": "How sensitive is the data in these cases?"
}
},
"description": "Optional: the six readiness-scan answers, the same format as answers in run_readiness_scan. Adds the score and the recommended start as line 10 of the brief.",
"additionalProperties": false
},
"preferred_start": {
"enum": [
"mapping",
"sprint",
"fde",
"unsure"
],
"type": "string",
"default": "unsure",
"description": "Preferred starting point: mapping, sprint, fde or unsure (default)."
},
"data_sensitivity": {
"enum": [
"low",
"medium",
"high-classified",
"high-unclear"
],
"type": "string",
"description": "How sensitive the data is: low, medium, high-classified (high, classified per field) or high-unclear (high, not yet classified)."
},
"known_outcome_cases": {
"enum": [
"lt50",
"50-200",
"200-1000",
"gt1000",
"unknown"
],
"type": "string",
"description": "How many historical cases with a known outcome can be pulled: lt50 (fewer than 50), 50-200, 200-1000, gt1000 (more than 1,000) or unknown."
}
},
"additionalProperties": false
}