AGILEX Docs is an MCP server published by ai.agilex.service, hosted at service.agilex.ai. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 5 tools, including search_docs, find_in_doc, get_doc, list_docs, list_spaces.
Official AGILEX robotics product docs: manuals, CAN protocol, firmware, FAQ. Read-only.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Full-text search over the official AGILEX product documentation. Use this first for any question about AGILEX hardware: pinouts, CAN protocol details, baud rate, firmware upgrade, error codes, LED/beep meanings, installation, calibration, SDK usage. Args: query: Chinese or English keywords. Include the product name (piper / pika / nero / ranger / limo / scout / bunker / hunter / tracer / umr) plus the concept, e.g. "piper CAN 波特率". limit: 1-25 results, default 8. space: optional space slug or name fragment to narrow the search, e.g. "agx-chassis-manual-cn-en" or "底盘使用手册". Returns JSON: {query, count, results:[{doc_id,title,space,url,score,chars,snippet}]}. ``count`` is the number of results in this reply (0-``limit``). Pages whose title carries 【未发】/【暂不对外】 are not offered for reading and never appear here — they are unpublished, not missing. ``doc_id`` is what ``get_doc`` expects.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query * | string | |
| space | string |
{
"name": "search_docs",
"description": "Full-text search over the official AGILEX product documentation.\n\n Use this first for any question about AGILEX hardware: pinouts, CAN\n protocol details, baud rate, firmware upgrade, error codes, LED/beep\n meanings, installation, calibration, SDK usage.\n\n Args:\n query: Chinese or English keywords. Include the product name\n (piper / pika / nero / ranger / limo / scout / bunker / hunter /\n tracer / umr) plus the concept, e.g. \"piper CAN 波特率\".\n limit: 1-25 results, default 8.\n space: optional space slug or name fragment to narrow the search,\n e.g. \"agx-chassis-manual-cn-en\" or \"底盘使用手册\".\n\n Returns JSON: {query, count, results:[{doc_id,title,space,url,score,chars,snippet}]}.\n ``count`` is the number of results in this reply (0-``limit``). Pages whose\n title carries 【未发】/【暂不对外】 are not offered for reading and never\n appear here — they are unpublished, not missing.\n ``doc_id`` is what ``get_doc`` expects.\n ",
"inputSchema": {
"type": "object",
"title": "search_docsArguments",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 8,
"maximum": 25,
"minimum": 1
},
"query": {
"type": "string",
"title": "Query"
},
"space": {
"type": "string",
"title": "Space",
"default": ""
}
}
},
"outputSchema": {
"type": "object",
"title": "search_docsOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Locate a passage *inside* one manual, without paging through it. Use this after ``search_docs`` whenever you need a specific table, command or error code rather than the whole page — including short documents, because manuals commonly open with a preamble and page 1 rarely answers a question. It returns the exact ``offset`` of each match, so one ``get_doc(doc_id, offset=...)`` lands on the right section. Prefer this over repeatedly calling ``get_doc`` with increasing offsets. Args: doc_id: id from ``search_docs`` (also accepts the page slug). query: the *concept*, not the product name — e.g. "波特率" or "急停 接线". Terms that already appear in this page's title are ignored, because ``search_docs`` picked the page by them; passing the product name again only adds noise. Generic words that appear in nearly every manual are down-weighted, so one distinctive term is enough. limit: 1-10 passages, default 5. Matching is OR, not AND: a passage is returned when it contains at least one term with enough weight. Terms that are absent from this page therefore do **not** force a zero result — check ``missing_terms`` to see which of your words this page never mentions, and ``matched_terms`` for the ones it does. A query made only of stop words (or nothing) returns ``count: 0`` with a hint. Returns JSON: {doc_id,title,space,url,chars,query,count,returned, matched_terms,missing_terms,hits:[{offset,heading,score,matched,excerpt}], hint}. ``count`` is the total number of matched passages; ``returned`` is how many are in ``hits`` (capped by ``limit``). ``heading`` is the nearest heading above the passage; ``offset`` is absolute in the page body.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query * | string | |
| doc_id * | string |
Read one documentation page as Markdown. Call this with a ``doc_id`` returned by ``search_docs`` (or a slug such as ``ymZimX7JLe``). Manuals are often 20k-60k characters, so this tool paginates: if the reply has ``truncated: true`` and a ``next_offset``, call again with that ``offset`` to continue. Do not re-request the same offset. Args: doc_id: id from search_docs (also accepts the page slug). max_chars: characters per call, default 20000, max 120000. offset: start position, default 0. Returns JSON: {doc_id,title,space,url,chars,offset,returned,max_chars, truncated,next_offset,updated_at,content}. Always cite ``url``. If the page has no body (folder or unwritten page), the reply has ``empty: true`` and a hint — do not retry with other offsets. A page whose title marks it unpublished returns ``unpublished: true`` with empty content; that is a publication decision, not a missing document.
| Parameter | Type | Description |
|---|---|---|
| doc_id * | string | |
| offset | integer | |
| max_chars | integer |
{
"name": "get_doc",
"description": "Read one documentation page as Markdown.\n\n Call this with a ``doc_id`` returned by ``search_docs`` (or a slug such as\n ``ymZimX7JLe``). Manuals are often 20k-60k characters, so this tool\n paginates: if the reply has ``truncated: true`` and a ``next_offset``,\n call again with that ``offset`` to continue. Do not re-request the same\n offset.\n\n Args:\n doc_id: id from search_docs (also accepts the page slug).\n max_chars: characters per call, default 20000, max 120000.\n offset: start position, default 0.\n\n Returns JSON: {doc_id,title,space,url,chars,offset,returned,max_chars,\n truncated,next_offset,updated_at,content}. Always cite ``url``.\n If the page has no body (folder or unwritten page), the reply has\n ``empty: true`` and a hint — do not retry with other offsets. A page whose\n title marks it unpublished returns ``unpublished: true`` with empty\n content; that is a publication decision, not a missing document.\n ",
"inputSchema": {
"type": "object",
"title": "get_docArguments",
"required": [
"doc_id"
],
"properties": {
"doc_id": {
"type": "string",
"title": "Doc Id"
},
"offset": {
"type": "integer",
"title": "Offset",
"default": 0,
"minimum": 0
},
"max_chars": {
"type": "integer",
"title": "Max Chars",
"default": 20000,
"maximum": 120000,
"minimum": 1
}
}
},
"outputSchema": {
"type": "object",
"title": "get_docOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List documented pages, optionally inside one space. Use when the caller wants an inventory ("what manuals exist for ranger") rather than an answer. Args: space: optional space slug or name fragment. limit: 1-300, default 100. offset: pagination offset, must be >= 0. Returns JSON: {space, count, offset, docs:[{doc_id,title,space,url,chars}]}. ``count`` is the number of docs in this page; compare it with ``limit`` to decide whether to request the next page. There is no total field — use ``list_spaces`` for per-space counts.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| space | string | |
| offset | integer |
{
"name": "list_docs",
"description": "List documented pages, optionally inside one space.\n\n Use when the caller wants an inventory (\"what manuals exist for ranger\")\n rather than an answer.\n\n Args:\n space: optional space slug or name fragment.\n limit: 1-300, default 100.\n offset: pagination offset, must be >= 0.\n\n Returns JSON: {space, count, offset, docs:[{doc_id,title,space,url,chars}]}.\n ``count`` is the number of docs in this page; compare it with ``limit`` to\n decide whether to request the next page. There is no total field — use\n ``list_spaces`` for per-space counts.\n ",
"inputSchema": {
"type": "object",
"title": "list_docsArguments",
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 100,
"maximum": 300,
"minimum": 1
},
"space": {
"type": "string",
"title": "Space",
"default": ""
},
"offset": {
"type": "integer",
"title": "Offset",
"default": 0,
"minimum": 0
}
}
},
"outputSchema": {
"type": "object",
"title": "list_docsOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List the public documentation spaces with page counts. Call this when the caller is unsure which product family a document belongs to, or to explain coverage. Returns JSON: {count, spaces:[{space,name,docs,chars}]}.
No parameters.
{
"name": "list_spaces",
"description": "List the public documentation spaces with page counts.\n\n Call this when the caller is unsure which product family a document\n belongs to, or to explain coverage.\n\n Returns JSON: {count, spaces:[{space,name,docs,chars}]}.\n ",
"inputSchema": {
"type": "object",
"title": "list_spacesArguments",
"properties": {}
},
"outputSchema": {
"type": "object",
"title": "list_spacesOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}AGILEX (松灵机器人) product documentation. Use this server BEFORE writing or explaining integration code for AGILEX hardware (piper, pika, nero, ranger, limo, scout, bunker, hunter, tracer, umr, cobot_magic, aloha). It contains the official user manuals, CAN/protocol references, firmware notes, FAQ and field-service procedures that shipped with those products. Workflow: 1. `search_docs` with the model name plus the concept you need (e.g. "piper CAN 波特率", "ranger mini 固件升级"). 2. Once you have a `doc_id`, `find_in_doc` is usually the fastest way to a specific passage — pass the concept ("波特率", "急停 接线"), not the product name. Then read it with `get_doc(doc_id, offset=...)`. Call `get_doc` from offset 0 only when you want the whole page from the top; note that manuals often open with a preamble, so page 1 rarely answers a specific question. Follow `next_offset` when you need the rest of a long section. 3. Cite the `url` field so the user can open the original page. Chinese and English titles both appear in the corpus; search in Chinese when the product docs are Chinese. Know when to stop: search at most twice per topic. If those results are only weakly related — the titles and snippets do not actually discuss the concept you asked about — stop and tell the user the documentation does not cover it. Do not keep rephrasing the query, and never guess a protocol detail or a pinout to fill the gap. A search that returns nothing, or a `find_in_doc` with zero hits, means the same thing: say so instead of inventing an answer.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.
{
"name": "find_in_doc",
"description": "Locate a passage *inside* one manual, without paging through it.\n\n Use this after ``search_docs`` whenever you need a specific table, command\n or error code rather than the whole page — including short documents,\n because manuals commonly open with a preamble and page 1 rarely answers a\n question. It returns the exact ``offset`` of each match, so one\n ``get_doc(doc_id, offset=...)`` lands on the right section.\n\n Prefer this over repeatedly calling ``get_doc`` with increasing offsets.\n\n Args:\n doc_id: id from ``search_docs`` (also accepts the page slug).\n query: the *concept*, not the product name — e.g. \"波特率\" or\n \"急停 接线\". Terms that already appear in this page's title are\n ignored, because ``search_docs`` picked the page by them; passing\n the product name again only adds noise. Generic words that appear\n in nearly every manual are down-weighted, so one distinctive term\n is enough.\n limit: 1-10 passages, default 5.\n\n Matching is OR, not AND: a passage is returned when it contains at least\n one term with enough weight. Terms that are absent from this page therefore\n do **not** force a zero result — check ``missing_terms`` to see which of\n your words this page never mentions, and ``matched_terms`` for the ones it\n does. A query made only of stop words (or nothing) returns ``count: 0``\n with a hint.\n\n Returns JSON: {doc_id,title,space,url,chars,query,count,returned,\n matched_terms,missing_terms,hits:[{offset,heading,score,matched,excerpt}],\n hint}. ``count`` is the total number of matched passages; ``returned`` is\n how many are in ``hits`` (capped by ``limit``). ``heading`` is the nearest\n heading above the passage; ``offset`` is absolute in the page body.\n ",
"inputSchema": {
"type": "object",
"title": "find_in_docArguments",
"required": [
"doc_id",
"query"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 5,
"maximum": 10,
"minimum": 1
},
"query": {
"type": "string",
"title": "Query"
},
"doc_id": {
"type": "string",
"title": "Doc Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "find_in_docOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}