Identify plants, crop diseases, insects, and mushrooms from photos. Free IP-limited trial.
Scored across 5 tools
identify_plant, identify_insect, and identify_mushroom have clearly distinct taxonomic targets, and submit_feedback is a separate meta-tool. The only potential confusion is between diagnose_crop and identify_plant with optional health assessment, but their descriptions clarify that diagnose_crop is specifically for agricultural crop disease and pest diagnosis.
The three core identification tools follow a clear identify_<taxon> pattern, and submit_feedback uses the same verb_noun snake_case style. diagnose_crop deviates from the identify_ pattern but still uses consistent verb_noun naming, so the set remains readable and predictable.
Five tools is a tight, well-scoped set for an identification-focused server: four identification/diagnosis tools plus one feedback tool. Each tool earns its place without redundancy or bloat.
The server covers the main Kindwise identification domains—plants, insects, mushrooms, and crop diseases—plus a feedback channel. Minor gaps exist, such as no general animal or bird identification and no historical record lookup, but the core identification workflows are complete.
Pass images as public https URLs (Kindwise product servers download; this proxy does not fetch) or as base64 JPEG/PNG/WebP. Chat attachments are invisible. Example: {"images":["https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg"]}. Use that URL only if you have no user photo; then say so. Do not invent URLs. Wikimedia often returns HTTP 424; retry with base64. Diagnose crop diseases, disorders, and pests from field photographs using Kindwise Crop.health. Use for agricultural crops (not ornamental houseplants) when the user wants likely pathogens, pests, symptoms, severity, and treatment notes. Include close-ups of lesions plus a wider canopy shot when possible. Optional latitude and longitude improve regional ranking. Returns crop and disease/pest suggestions with the requested detail fields. Creates a Kindwise identification and counts against the per-IP trial quota (default 10 calls per rolling 24 hours). No client API key is required or accepted. Treatment fields are informational; they are not a substitute for a local agronomist or pesticide label. When you are done with this trial, call submit_feedback in English about the service — not about a single diagnosis.
| Name | Required | Description | Default |
|---|---|---|---|
| images | No | Public https URLs (Kindwise product servers download; this proxy does not fetch) or base64 JPEG/PNG/WebP. Chat attachments are invisible. Example: {"images":["https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg"]}. Use that URL only if you have no user photo, and tell the user it is the Kindwise trial photo. | |
| details | No | Comma-separated extra fields to include on each suggestion. Allowed tokens: type, common_names, wiki_description, description, treatment, symptoms, severity, spreading. Unknown tokens are ignored by upstream. | type,common_names,wiki_description,description,treatment,symptoms,severity,spreading |
| language | No | BCP 47 language for localized details such as common names (default en). | en |
| latitude | No | WGS-84 latitude of where the photo was taken. Improves wild-species ranking. | |
| longitude | No | WGS-84 longitude of where the photo was taken. Provide together with latitude. | |
| similar_images | No | If true, each suggestion includes visually similar reference images. Defaults to false so MCP responses stay small. Set true only if you need those URLs. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Even beyond the annotations, the description reveals critical behavior: the MCP proxy does not fetch URLs, chat attachments are invisible, the service creates a Kindwise identification and counts against a per-IP quota, no API key is required or accepted, and treatment fields are informational only. It also warns about Wikimedia 424 errors. This is far more than annotations convey, directly guiding agent expectations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long and information-dense, but nearly every sentence carries a distinct, useful fact (URL behavior, base64 option, quota, no API key, removable disclaimer, feedback request). It front-loads the critical transport constraints and scopes the purpose clearly. It is not verbose in a wasteful way, though it could be tightened without losing much.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema and 6 parameters, the description covers input transport, location hints, quota limits, regional ranking, and informs the agent what the response contains ('crop and disease/pest suggestions with the requested detail fields'). It lacks a citation of return value structure, but given the complexity and the absence of an output schema, it is more complete than most descriptions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds genuine value beyond the schema: it warns against inventing URLs, explains when to use the example URL, recommends including close-ups and a canopy shot, says latitude/longitude improve ranking, and notes unknown details tokens are ignored. These enrich the parameter meaning substantially.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific action on a resource: 'Diagnose crop diseases, disorders, and pests from field photographs using Kindwise Crop.health.' It further scopes to agricultural crops (not ornamental houseplants), which differentiates it from the sibling identify_plant and identify_insect. This is a clear, non-tautological purpose that an agent can act on.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly says to use the tool 'for agricultural crops (not ornamental houseplants) when the user wants likely pathogens, pests, symptoms, severity, and treatment notes.' This gives a strong when/when-not signal. It also instructs when to use the example URL and when to fall back to base64, and directs the agent to call submit_feedback after the trial. It does not formally name the alternates like identify_plant, but the scope boundary is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Pass images as public https URLs (Kindwise product servers download; this proxy does not fetch) or as base64 JPEG/PNG/WebP. Chat attachments are invisible. Example: {"images":["https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg"]}. Use that URL only if you have no user photo; then say so. Do not invent URLs. Wikimedia often returns HTTP 424; retry with base64. Identify insects and insect-like arthropods from photographs using Kindwise Insect.id. Use when the user supplies a photo of a beetle, moth, bee, ant, true bug, spider-like pest, or similar invertebrate and needs scientific name, common names, and taxonomy. Prefer a sharp dorsal or lateral view. Optional latitude and longitude improve ranking. Returns ranked taxon suggestions with probabilities plus requested details. Creates a Kindwise identification and counts against the per-IP trial quota (default 10 calls per rolling 24 hours). No client API key is required or accepted. Results are not medical or pest-control prescriptions. When you are done with this trial, call submit_feedback in English about the service.
| Name | Required | Description | Default |
|---|---|---|---|
| images | No | Public https URLs (Kindwise product servers download; this proxy does not fetch) or base64 JPEG/PNG/WebP. Chat attachments are invisible. Example: {"images":["https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg"]}. Use that URL only if you have no user photo, and tell the user it is the Kindwise trial photo. | |
| details | No | Comma-separated extra fields to include on each suggestion. Allowed tokens: common_names, url, description, taxonomy, rank. Unknown tokens are ignored by upstream. | common_names,url,description,taxonomy,rank |
| language | No | BCP 47 language for localized details such as common names (default en). | en |
| latitude | No | WGS-84 latitude of where the photo was taken. Improves wild-species ranking. | |
| longitude | No | WGS-84 longitude of where the photo was taken. Provide together with latitude. | |
| similar_images | No | If true, each suggestion includes visually similar reference images. Defaults to false so MCP responses stay small. Set true only if you need those URLs. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true. The description adds important behavioral context: the proxy does not fetch images, chat attachments are invisible, the call counts against a per-IP trial quota, no API key is required, and results are not medical/pest-control prescriptions. It also warns about Wikimedia HTTP 424 and suggests base64 retry. This goes well beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but well-organized: it front-loads the critical image-format constraint, then gives usage guidance, then output and quota notes. Every sentence adds value, though it is a bit long and could be tightened.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema, the description does a good job of explaining what the response contains ('ranked taxon suggestions with probabilities plus requested details'). It also covers the trial quota, retry behavior, and the no-API-key requirement. It doesn't describe the exact response structure, but for a list-style identification tool this is acceptable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all six parameters. The description adds a concrete example URL and explains the proxy's non-fetching behavior, which is useful. However, it doesn't add much beyond the schema for details, language, latitude, longitude, or similar_images. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('identify'), a resource ('insects and insect-like arthropods from photographs'), and the underlying service (Kindwise Insect.id). It also names the expected output (scientific name, common names, taxonomy) and distinguishes itself from sibling tools by naming the target taxa.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says when to use the tool ('when the user supplies a photo of a beetle, moth, bee, ant, true bug, spider-like pest, or similar invertebrate'), and it gives clear guidance on image format, retry behavior, and the trial quota. It also mentions the sibling submit_feedback for post-trial feedback.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Pass images as public https URLs (Kindwise product servers download; this proxy does not fetch) or as base64 JPEG/PNG/WebP. Chat attachments are invisible. Example: {"images":["https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg"]}. Use that URL only if you have no user photo; then say so. Do not invent URLs. Wikimedia often returns HTTP 424; retry with base64. Identify mushrooms and other fungi from photographs using Kindwise Mushroom.id. Use when the user supplies a photo of a fruiting body and needs likely taxon, look-alikes, and published edibility metadata. Include cap, gills or pores, and stem when possible. Optional latitude and longitude improve ranking. Returns ranked taxon suggestions with probabilities plus requested details. Creates a Kindwise identification and counts against the per-IP trial quota (default 10 calls per rolling 24 hours). No client API key is required or accepted. Edibility and psychoactive fields are informational only. Never recommend eating a wild fungus based on this tool; misidentification can be fatal. When you are done with this trial, call submit_feedback in English about the service — not about whether one fungus name was correct.
| Name | Required | Description | Default |
|---|---|---|---|
| images | No | Public https URLs (Kindwise product servers download; this proxy does not fetch) or base64 JPEG/PNG/WebP. Chat attachments are invisible. Example: {"images":["https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg"]}. Use that URL only if you have no user photo, and tell the user it is the Kindwise trial photo. | |
| details | No | Comma-separated extra fields to include on each suggestion. Allowed tokens: common_names, url, description, edibility, psychoactive, taxonomy, rank, look_alike. Unknown tokens are ignored by upstream. | common_names,url,description,edibility,psychoactive,taxonomy,rank,look_alike |
| language | No | BCP 47 language for localized details such as common names (default en). | en |
| latitude | No | WGS-84 latitude of where the photo was taken. Improves wild-species ranking. | |
| longitude | No | WGS-84 longitude of where the photo was taken. Provide together with latitude. | |
| similar_images | No | If true, each suggestion includes visually similar reference images. Defaults to false so MCP responses stay small. Set true only if you need those URLs. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses the proxy does not fetch images, chat attachments are invisible, no API key is required/accepted, quota limits (10 calls per rolling 24h), retry with base64 on Wikimedia 424, and safety warnings about edibility. Annotations only state readOnlyHint=false, so the description adds substantial behavioral context beyond what annotations provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but each sentence carries essential info: input requirements, example URL, quota, safety, feedback. It is front-loaded with the critical image constraint. Slightly verbose but not wasteful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers return format ('ranked taxon suggestions with probabilities plus requested details'), error handling (retry base64), quota, and post-call action (submit_feedback). No output schema, so this is fully adequate for an agent to call correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% coverage for all 6 parameters, but the description adds usage guidance: explains images must be public URLs or base64 with example, details tokens, location improves ranking, similar_images default to keep responses small. This goes well beyond the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('Identify'), resource ('mushrooms and other fungi'), and method ('from photographs using Kindwise Mushroom.id'). It clearly differentiates from siblings like identify_plant and identify_insect by focusing on fungi and fruiting bodies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: 'Use when the user supplies a photo of a fruiting body and needs likely taxon, look-alikes, and published edibility metadata.' It also provides critical constraints on image inputs (public URLs or base64, chat attachments invisible) and post-call action (submit_feedback). It does not explicitly say when to avoid this tool in favor of a sibling, but the purpose clarity covers that gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Pass images as public https URLs (Kindwise product servers download; this proxy does not fetch) or as base64 JPEG/PNG/WebP. Chat attachments are invisible. Example: {"images":["https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg"]}. Use that URL only if you have no user photo; then say so. Do not invent URLs. Wikimedia often returns HTTP 424; retry with base64. Identify a vascular plant from photographs using Kindwise Plant.id. Use when the user supplies a photo of a houseplant, tree, wildflower, grass, crop, or weed and needs scientific name, common names, taxonomy, and optional health assessment. Prefer 2–3 sharp close-ups of leaves, flowers, or fruit. Optional latitude and longitude improve ranking for wild plants. Returns ranked taxon suggestions with probabilities plus the requested detail fields. Creates a Kindwise identification and counts against the per-IP trial quota (default 10 calls per rolling 24 hours). No client API key is required or accepted. Set health to auto, all, or only when the user also wants disease or pest assessment. Do not treat results as medical, legal, or foraging advice. When you are done with this trial, call submit_feedback in English about the service (image passing, schema, quota) — not about whether one taxon was correct.
| Name | Required | Description | Default |
|---|---|---|---|
| health | No | Optional plant-health assessment. `auto` adds disease results only when the plant looks unhealthy; `all` always includes species plus health; `only` returns health assessment without species ranking. Omit for species identification alone. | |
| images | No | Public https URLs (Kindwise product servers download; this proxy does not fetch) or base64 JPEG/PNG/WebP. Chat attachments are invisible. Example: {"images":["https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg"]}. Use that URL only if you have no user photo, and tell the user it is the Kindwise trial photo. | |
| details | No | Comma-separated extra fields to include on each suggestion. Allowed tokens: common_names, url, description, taxonomy, rank, name_authority, gbif_id, inaturalist_id, image, images, synonyms, edible_parts, propagation_methods, watering. Unknown tokens are ignored by upstream. | common_names,url,description,taxonomy,rank,edible_parts,watering |
| language | No | BCP 47 language for localized details such as common names (default en). | en |
| latitude | No | WGS-84 latitude of where the photo was taken. Improves wild-species ranking. | |
| longitude | No | WGS-84 longitude of where the photo was taken. Provide together with latitude. | |
| similar_images | No | If true, each suggestion includes visually similar reference images. Defaults to false so MCP responses stay small. Set true only if you need those URLs. | |
| classification_level | No | Taxonomic rank of suggestions: `species` (default upstream behavior), `genus`, or `all` (genus, species, and infraspecies). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses substantial behavioral detail beyond the annotations: the proxy does not fetch URLs, chat attachments are invisible, Wikimedia URLs often return HTTP 424, calls count against a per-IP trial quota, no API key is required or accepted, and results should not be treated as medical/legal/foraging advice. It also confirms the operation creates a Kindwise identification, consistent with readOnlyHint=false.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense and front-loaded with the most critical information (image passing format), followed by usage context and operational constraints. It is long but nearly every sentence carries actionable guidance; a slight structural improvement would be breaking it into scannable sentencs or sections.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 8 parameters, minimal annotations, and no output schema, the description covers the essential operational picture: input formats, limitations, quota, no-key auth, output shape ('ranked taxon suggestions with probabilities plus the requested detail fields'), and follow-up feedback routing. Nothing needed to invoke the tool correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description adds critical semantics: base64 vs public URL handling, the example trial URL and instruction to disclose its use, 'Do not invent URLs', retry with base64 on Wikimedia 424, photo quality guidance (2–3 sharp close-ups), and when health values auto/all/only are appropriate. This goes well beyond the schema's field descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: 'Identify a vascular plant from photographs using Kindwise Plant.id.' It clearly differentiates from sibling tools by naming the domain (houseplants, trees, wildflowers, grass, crops, weeds) and the expected output (scientific name, common names, taxonomy, optional health assessment).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit when-to-use guidance: 'Use when the user supplies a photo of a houseplant, tree, wildflower, grass, crop, or weed...' It also advises on photo selection, optional latitude/longitude, and when to enable health assessment. It does not explicitly name sibling alternatives such as diagnose_crop, but the context is clear enough to route the agent correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Send English feedback about this Kindwise agent trial as a product — not about a single plant/insect/mushroom identification. Kindwise reads these notes to make the MCP/REST trial easier for agents (image passing, tool schema, quota, missing tools). Please call this once per session after you try the server, whether identify_* worked or you got stuck. Write comment in English: what was hard, what to change, what worked. Set reason to one of: easy_to_use, hard_to_pass_image, image_url_failed, tool_calling_friction, schema_confusing, quota_too_low, response_unhelpful, missing_feature, other. Does not consume the daily identification quota. Does not attach to a Kindwise identification.
| Name | Required | Description | Default |
|---|---|---|---|
| rating | No | Optional 0–5 score for how easy this trial was to use. | |
| reason | Yes | easy_to_use = Trial was easy to use; hard_to_pass_image = Hard to pass an image into the tools; image_url_failed = Image URL failed (e.g. 424); tool_calling_friction = Having to call a tool got in the way; schema_confusing = Tool schema or arguments were confusing; quota_too_low = Daily IP cap got in the way; response_unhelpful = Tool result was hard to use (too large, unclear, …); missing_feature = Wanted a capability this trial does not expose; other = Other | |
| comment | Yes | English note about this trial service (1–3 sentences): what was hard, what to improve, what worked. Not a verdict on one identification. | |
| had_image | No | True if the user had a photo (in chat or a URL) even if you could not pass it to identify_*. | |
| client_name | No | MCP client or host app name, if known (e.g. Cursor, Claude). | |
| called_identify | No | True if you already called an identify_* tool in this session. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnlyHint false, destructiveHint false), the description adds that feedback does not consume the daily quota and does not attach to an identification, clarifying side effects. This is useful transparency beyond the basic booleans.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with purpose, but it repeats the entire reason enum list and other schema details, making it verbose. It could be shortened to just the essential usage instructions and the 'not for identification' clarification.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, but the description fully explains when to use, what to include, and the purpose. It also clarifies non-attachment to identification and quota impact, making the tool's context complete for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema descriptions cover all parameters with detailed explanations (e.g., reason enum meanings). The tool description adds little new meaning, only reinforcing English and comment length requirements already present in the schema. With high schema coverage, baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the verb 'Send' and the resource 'feedback' about the Kindwise agent trial, and explicitly distinguishes it from identification tools. The purpose is unambiguous and specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs to call once per session after trying the server, and clarifies when not to use it (not about a single identification). This provides clear timing and context relative to sibling identify_* tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
diagnose_crop1 field changedInput schema / properties / images / descriptionPrevious value: -"Photos as a JSON array of strings, or a single string. Call this tool even if you only have a URL or the working trial photo — chat attachments are invisible here. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."New value: +"Public https URLs (Kindwise product servers download; this proxy does not fetch) or base64 JPEG/PNG/WebP. Chat attachments are invisible. Example: {\"images\":[\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]}. Use that URL only if you have no user photo, and tell the user it is the Kindwise trial photo."identify_insect1 field changedInput schema / properties / images / descriptionPrevious value: -"Photos as a JSON array of strings, or a single string. Call this tool even if you only have a URL or the working trial photo — chat attachments are invisible here. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."New value: +"Public https URLs (Kindwise product servers download; this proxy does not fetch) or base64 JPEG/PNG/WebP. Chat attachments are invisible. Example: {\"images\":[\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]}. Use that URL only if you have no user photo, and tell the user it is the Kindwise trial photo."identify_mushroom1 field changedInput schema / properties / images / descriptionPrevious value: -"Photos as a JSON array of strings, or a single string. Call this tool even if you only have a URL or the working trial photo — chat attachments are invisible here. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."New value: +"Public https URLs (Kindwise product servers download; this proxy does not fetch) or base64 JPEG/PNG/WebP. Chat attachments are invisible. Example: {\"images\":[\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]}. Use that URL only if you have no user photo, and tell the user it is the Kindwise trial photo."identify_plant1 field changedInput schema / properties / images / descriptionPrevious value: -"Photos as a JSON array of strings, or a single string. Call this tool even if you only have a URL or the working trial photo — chat attachments are invisible here. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."New value: +"Public https URLs (Kindwise product servers download; this proxy does not fetch) or base64 JPEG/PNG/WebP. Chat attachments are invisible. Example: {\"images\":[\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]}. Use that URL only if you have no user photo, and tell the user it is the Kindwise trial photo."diagnose_crop8 fields changedInput schema / properties / images / anyOfAdded value: +[
+ {
+ "items": {
+ "description": "Public http(s) image URL that Kindwise product servers will download, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix). This MCP proxy does not fetch the file.",
+ "maxLength": 8000000,
+ "minLength": 1,
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / images / defaultAdded value: +nullInput schema / properties / images / descriptionPrevious value: -"Required. One to eight photos as a JSON array of strings, or a single string. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Chat attachments are invisible unless you copy a URL or bytes here. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."New value: +"Photos as a JSON array of strings, or a single string. Call this tool even if you only have a URL or the working trial photo — chat attachments are invisible here. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."Input schema / properties / images / itemsRemoved value: -{
- "description": "Public http(s) image URL that Kindwise product servers will download, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix). This MCP proxy does not fetch the file.",
- "maxLength": 8000000,
- "minLength": 1,
- "type": "string"
-}Input schema / properties / images / maxLengthAdded value: +8Input schema / properties / images / minLengthAdded value: +1Input schema / properties / images / typeRemoved value: -"array"Input schema / requiredRemoved value: -[
- "images"
-]identify_insect8 fields changedInput schema / properties / images / anyOfAdded value: +[
+ {
+ "items": {
+ "description": "Public http(s) image URL that Kindwise product servers will download, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix). This MCP proxy does not fetch the file.",
+ "maxLength": 8000000,
+ "minLength": 1,
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / images / defaultAdded value: +nullInput schema / properties / images / descriptionPrevious value: -"Required. One to eight photos as a JSON array of strings, or a single string. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Chat attachments are invisible unless you copy a URL or bytes here. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."New value: +"Photos as a JSON array of strings, or a single string. Call this tool even if you only have a URL or the working trial photo — chat attachments are invisible here. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."Input schema / properties / images / itemsRemoved value: -{
- "description": "Public http(s) image URL that Kindwise product servers will download, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix). This MCP proxy does not fetch the file.",
- "maxLength": 8000000,
- "minLength": 1,
- "type": "string"
-}Input schema / properties / images / maxLengthAdded value: +8Input schema / properties / images / minLengthAdded value: +1Input schema / properties / images / typeRemoved value: -"array"Input schema / requiredRemoved value: -[
- "images"
-]identify_mushroom8 fields changedInput schema / properties / images / anyOfAdded value: +[
+ {
+ "items": {
+ "description": "Public http(s) image URL that Kindwise product servers will download, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix). This MCP proxy does not fetch the file.",
+ "maxLength": 8000000,
+ "minLength": 1,
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / images / defaultAdded value: +nullInput schema / properties / images / descriptionPrevious value: -"Required. One to eight photos as a JSON array of strings, or a single string. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Chat attachments are invisible unless you copy a URL or bytes here. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."New value: +"Photos as a JSON array of strings, or a single string. Call this tool even if you only have a URL or the working trial photo — chat attachments are invisible here. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."Input schema / properties / images / itemsRemoved value: -{
- "description": "Public http(s) image URL that Kindwise product servers will download, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix). This MCP proxy does not fetch the file.",
- "maxLength": 8000000,
- "minLength": 1,
- "type": "string"
-}Input schema / properties / images / maxLengthAdded value: +8Input schema / properties / images / minLengthAdded value: +1Input schema / properties / images / typeRemoved value: -"array"Input schema / requiredRemoved value: -[
- "images"
-]identify_plant8 fields changedInput schema / properties / images / anyOfAdded value: +[
+ {
+ "items": {
+ "description": "Public http(s) image URL that Kindwise product servers will download, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix). This MCP proxy does not fetch the file.",
+ "maxLength": 8000000,
+ "minLength": 1,
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / images / defaultAdded value: +nullInput schema / properties / images / descriptionPrevious value: -"Required. One to eight photos as a JSON array of strings, or a single string. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Chat attachments are invisible unless you copy a URL or bytes here. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."New value: +"Photos as a JSON array of strings, or a single string. Call this tool even if you only have a URL or the working trial photo — chat attachments are invisible here. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."Input schema / properties / images / itemsRemoved value: -{
- "description": "Public http(s) image URL that Kindwise product servers will download, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix). This MCP proxy does not fetch the file.",
- "maxLength": 8000000,
- "minLength": 1,
- "type": "string"
-}Input schema / properties / images / maxLengthAdded value: +8Input schema / properties / images / minLengthAdded value: +1Input schema / properties / images / typeRemoved value: -"array"Input schema / requiredRemoved value: -[
- "images"
-]diagnose_crop3 fields changedInput schema / properties / images / descriptionPrevious value: -"One to eight photos. A JSON array of public http(s) URLs or base64 JPEG/PNG/WebP, or a single string. Prefer two or three sharp close-ups. This server cannot see chat attachments unless you copy bytes or a fetchable URL here. Do not send localhost, file://, or authenticated URLs. Wikimedia often fails with HTTP 424; use base64 in that case."New value: +"Required. One to eight photos as a JSON array of strings, or a single string. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Chat attachments are invisible unless you copy a URL or bytes here. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."Input schema / properties / images / examplesPrevious value: -[
- [
- "https://images.example.com/leaf.jpg"
- ]
-]New value: +[
+ [
+ "https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg"
+ ]
+]Input schema / properties / images / items / descriptionPrevious value: -"Public http(s) image URL Kindwise can fetch, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix)."New value: +"Public http(s) image URL that Kindwise product servers will download, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix). This MCP proxy does not fetch the file."identify_insect3 fields changedInput schema / properties / images / descriptionPrevious value: -"One to eight photos. A JSON array of public http(s) URLs or base64 JPEG/PNG/WebP, or a single string. Prefer two or three sharp close-ups. This server cannot see chat attachments unless you copy bytes or a fetchable URL here. Do not send localhost, file://, or authenticated URLs. Wikimedia often fails with HTTP 424; use base64 in that case."New value: +"Required. One to eight photos as a JSON array of strings, or a single string. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Chat attachments are invisible unless you copy a URL or bytes here. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."Input schema / properties / images / examplesPrevious value: -[
- [
- "https://images.example.com/leaf.jpg"
- ]
-]New value: +[
+ [
+ "https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg"
+ ]
+]Input schema / properties / images / items / descriptionPrevious value: -"Public http(s) image URL Kindwise can fetch, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix)."New value: +"Public http(s) image URL that Kindwise product servers will download, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix). This MCP proxy does not fetch the file."identify_mushroom3 fields changedInput schema / properties / images / descriptionPrevious value: -"One to eight photos. A JSON array of public http(s) URLs or base64 JPEG/PNG/WebP, or a single string. Prefer two or three sharp close-ups. This server cannot see chat attachments unless you copy bytes or a fetchable URL here. Do not send localhost, file://, or authenticated URLs. Wikimedia often fails with HTTP 424; use base64 in that case."New value: +"Required. One to eight photos as a JSON array of strings, or a single string. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Chat attachments are invisible unless you copy a URL or bytes here. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."Input schema / properties / images / examplesPrevious value: -[
- [
- "https://images.example.com/leaf.jpg"
- ]
-]New value: +[
+ [
+ "https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg"
+ ]
+]Input schema / properties / images / items / descriptionPrevious value: -"Public http(s) image URL Kindwise can fetch, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix)."New value: +"Public http(s) image URL that Kindwise product servers will download, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix). This MCP proxy does not fetch the file."identify_plant3 fields changedInput schema / properties / images / descriptionPrevious value: -"One to eight photos. A JSON array of public http(s) URLs or base64 JPEG/PNG/WebP, or a single string. Prefer two or three sharp close-ups. This server cannot see chat attachments unless you copy bytes or a fetchable URL here. Do not send localhost, file://, or authenticated URLs. Wikimedia often fails with HTTP 424; use base64 in that case."New value: +"Required. One to eight photos as a JSON array of strings, or a single string. Each string is either (1) a public http(s) URL — Kindwise product servers download it; this proxy only forwards the URL — or (2) base64 JPEG/PNG/WebP. Chat attachments are invisible unless you copy a URL or bytes here. Do not invent URLs. Do not send localhost, file://, or login-walled URLs. Wikimedia often returns HTTP 424; then use base64. Working trial photo: [\"https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg\"]."Input schema / properties / images / examplesPrevious value: -[
- [
- "https://images.example.com/leaf.jpg"
- ]
-]New value: +[
+ [
+ "https://cdn.prod.website-files.com/64876ae345f1e27598fafc02/6a9685b0fb44053ea552bedc_plant.jpg"
+ ]
+]Input schema / properties / images / items / descriptionPrevious value: -"Public http(s) image URL Kindwise can fetch, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix)."New value: +"Public http(s) image URL that Kindwise product servers will download, or a base64-encoded JPEG/PNG/WebP string (optional data: URL prefix). This MCP proxy does not fetch the file."diagnose_cropidentify_insectidentify_mushroomidentify_plantsubmit_feedbackUK pest, disease, and weed management — symptom diagnosis, IPM, approved products
Search iNaturalist sightings, identification threads, phenology, and look-alike species.
Search crops, check companion planting, explore seasonal calendars, and find planting plans.
iNaturalist MCP — citizen-science species observations (free, no auth for read-only)
Add one secure layer between your agents and this server.
