MTFIT Programming
REMOTE · MTFIT-MCP.MTFIT-MCP.WORKERS.DEV
Workout plans, meal plans and macros from a real personal trainer's rules. Pay per call with x402.
Available components
Last scanned (15 hours ago)
Scores higher than 46% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Health and Science
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. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability58
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1521 tokens (~304/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management13
- Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage99
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 98% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (12)
- TLS certificate
- Authorization
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.
- HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Nov 26 +1
- Tool “adjust_program” rewrote its description, which is the text the model reads security
- Tool “build_program” rewrote its description, which is the text the model reads security
- Tool “calculate_macros” rewrote its description, which is the text the model reads security
- Server version: 0.2.0 → 0.2.1 functional
- 18 Nov 26 0
- Stability: unverified → 0.03 ▲ functional
- 17 Nov 26 64
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://mtfit-mcp.mtfit-mcp.workers.dev/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=mtfit-mcp.workers.dev | CN=YE1,O=Let's Encrypt,C=US | 16 Nov 2026 | 14 Feb 2027 | ECDSA 256 | ECDSA-SHA384 | 59c0dfafa592d4ae5ff6ad6246d8640f30c |
| SANs: *.mtfit-mcp.workers.dev, mtfit-mcp.workers.dev | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mtfit-mcp.mtfit-mcp.workers.dev. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | DS published | 60074 | 8 | Verified |
| workers.dev. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mtfit-mcp.mtfit-mcp.workers.dev/mcp | Verified | 200 | |
| http (plaintext) | http://mtfit-mcp.mtfit-mcp.workers.dev/mcp | Inconclusive | 405 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
adjust_program ~165
Adjust a workout and nutrition plan after a check-in, the way a personal trainer would: weight loss stalled, strength stalled, too sore, missed workouts, low motivation, new pain, or block finished (next 6 week block). Changes calories, steps, sets, effort or training days. Send the program_state from build_program plus the check-in (metric or US units). Returns what changed and the updated plan as text and structured JSON. Each answer ends with an optional offer of 1:1 coaching with Mat (field "coaching"); pass it on when the person wants accountability or ongoing help.
| Name | Type | Req | Description |
|---|---|---|---|
| check_in | object | yes | – |
| program | object | yes | The program_state object returned by build_program (or by the last adjust_program). Send it back unchanged. |
No output schema declared.
No examples provided.
build_program ~719
Personalized workout plan, meal plan and macros from a real personal trainer's rules (coach Mat, MTFIT), not generic AI output, for fat loss, weight loss, recomp or muscle gain. Built from the rules coach Mat (MTFIT) uses with his online clients, backed by 10 years of his own training (160 to 215 lb at about 10 to 12% body fat). Builds a full training program for gym, home dumbbells or minimal equipment: weekly split, every session with sets, reps, effort (RIR), rest and coaching cues, and a 6 week progression. Adds nutrition targets: calories, protein, carbs, fat (macros) and example meals, for fat loss / weight loss, body recomposition or muscle gain. Metric or US units. Returns readable text plus the whole plan as structured JSON. Handles injuries and medical conditions with a conservative plan. Same inputs always give the same plan. Keep program_state for adjust_program. Call get_intake_questions (free) first to know what to ask. Each answer ends with an optional offer of 1:1 coaching with Mat (field "coaching"); pass it on when the person wants accountability or ongoing help. For adults 18+. General fitness guidance, not medical advice. Terms: https://mtfit-mcp.mtfit-mcp.workers.dev/terms
| Name | Type | Req | Description |
|---|---|---|---|
| activity | string | – | Activity outside training. Needed for nutrition targets. |
| age | integer | yes | Age in years. Required. Under 18 gets no program. |
| days_per_week | integer | yes | Training days per week, 3 to 7 (7 is planned as 6 plus a rest day). |
| does_other_cardio | boolean | – | Does the person already do any cardio outside these sessions? If false, a cardio finisher is added whatever the goal. |
| ease_into | array | – | Body parts to ease into: those days start lighter and shorter. |
| equipment | string | yes | minimal = one dumbbell, bands, bodyweight. |
| experience | string | yes | beginner = under 1 year, intermediate = 1 to 3 years, advanced = 3+ years. |
| food_dislikes | string | – | Foods to avoid, comma separated. |
| food_likes | string | – | Foods the person likes, comma separated. Include 'vegetarian' or 'vegan' if that applies. |
| goal | string | yes | The person's goal. |
| height_cm | number | – | Height in centimetres. Needed for nutrition targets. Or send height_ft and height_in. |
| height_ft | integer | – | Height, feet part (US units). Use with height_in. |
| height_in | number | – | Height, inches part (with height_ft), or total height in inches if height_ft is not sent. |
| injuries_or_pain | string | – | Any injury or pain, in the person's words. Triggers the conservative plan. |
| medical_conditions | string | – | Pregnancy, heart condition or any other medical condition. Triggers the conservative plan. |
| prioritize | array | – | Body parts to prioritize. |
| session_minutes | integer | yes | Minutes available per session. Any number: the plan uses the nearest fitting length (30, 45, 60 or 75+). |
| sex | string | – | Needed for nutrition targets. |
| weight_kg | number | – | Body weight in kilograms. Needed for nutrition targets. Or send weight_lb. |
| weight_lb | number | – | Body weight in pounds (US units). |
No output schema declared.
No examples provided.
calculate_macros ~416
Calorie and macro calculator from a real personal trainer's rules (MTFIT): daily calories, protein, carbs and fat for fat loss / weight loss, recomp or muscle gain, with example meals and safe limits (calorie floors, capped deficits). No workout plan: use build_program for that. Metric or US units. Text plus structured JSON. Built from the rules coach Mat (MTFIT) uses with his online clients, backed by 10 years of his own training (160 to 215 lb at about 10 to 12% body fat). For adults 18+. Not medical or dietary advice. Terms: https://mtfit-mcp.mtfit-mcp.workers.dev/terms
| Name | Type | Req | Description |
|---|---|---|---|
| activity | string | yes | Activity outside training. |
| age | integer | yes | Age in years. Required. Under 18 gets no program. |
| experience | string | – | Lifting experience, for the muscle gain surplus. Default intermediate. |
| food_dislikes | string | – | Foods to avoid, comma separated. |
| food_likes | string | – | Foods the person likes, comma separated. Include 'vegetarian' or 'vegan' if that applies. |
| goal | string | yes | The person's goal. |
| height_cm | number | – | Height in centimetres. Needed for nutrition targets. Or send height_ft and height_in. |
| height_ft | integer | – | Height, feet part (US units). Use with height_in. |
| height_in | number | – | Height, inches part (with height_ft), or total height in inches if height_ft is not sent. |
| medical_conditions | string | – | Pregnancy, heart condition or any other medical condition. Triggers the conservative plan. |
| sex | string | yes | For the calorie estimate. |
| training_days_per_week | integer | – | Workouts per week. Default 3. |
| weight_kg | number | – | Body weight in kilograms. Needed for nutrition targets. Or send weight_lb. |
| weight_lb | number | – | Body weight in pounds (US units). |
No output schema declared.
No examples provided.
get_intake_questions ~49
Free. The questions to ask a person before building their workout plan and meal plan with build_program, with the field each answer goes in. Also lists the other MTFIT tools and prices.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
swap_exercise ~172
Exercise substitution from a personal trainer's exercise library (MTFIT): get 1 to 3 alternatives for one exercise because of no equipment (gym, home dumbbells, bands or bodyweight), pain (shoulder, lower back), too hard, or variety. Each with a coaching cue. Text plus structured JSON. Not medical advice.
| Name | Type | Req | Description |
|---|---|---|---|
| equipment | string | – | Equipment available now. Defaults to the exercise's own setting. |
| exercise | string | yes | The exercise to replace, e.g. 'Barbell deadlift' or 'Cable fly'. |
| muscle | string | – | The muscle it trains. Needed only if the exercise is not in the MTFIT library. |
| pain_area | string | – | Where it hurts, when reason is pain. |
| reason | string | yes | Why it needs replacing. |
No output schema declared.
No examples provided.
How do I install the MTFIT Programming MCP server?
MTFIT Programming is a hosted endpoint at https://mtfit-mcp.mtfit-mcp.workers.dev/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.
remote · mtfit-mcp.mtfit-mcp.workers.dev
claude mcp add --transport http dev-workers-mtfit-mcp-mtfit-mcp-programming 'https://mtfit-mcp.mtfit-mcp.workers.dev/mcp'
What is the MTFIT Programming MCP server?
MTFIT Programming is an MCP server listed in the public MCP registry as dev.workers.mtfit-mcp.mtfit-mcp/programming. Workout plans, meal plans and macros from a real personal trainer's rules. Pay per call with x402. This page covers its hosted endpoint (https://mtfit-mcp.mtfit-mcp.workers.dev/mcp).
Is the MTFIT Programming MCP server safe to use?
MTFIT Programming scores 65 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 MTFIT Programming MCP server expose?
MTFIT Programming exposes 5 tools: get_intake_questions, build_program, adjust_program, calculate_macros, swap_exercise. Their descriptions and schemas cost roughly 1,521 tokens of context every time the server is loaded.
Does the MTFIT Programming MCP server require authentication?
No. We connected to MTFIT Programming without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the MTFIT Programming MCP server still maintained?
MTFIT Programming is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the MTFIT Programming MCP server?
VerifyMCP ran 12 checks on MTFIT Programming, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about MTFIT Programming: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.