Agent Docs
REMOTE · AGENT-DOCS-MCP.ONRENDER.COM
Search the official docs of Claude Code, Cursor, OpenAI Codex and MCP, refreshed daily.
Available components
Last scanned (6 hours ago)
Scores higher than 68% of remote servers
Reachable. Last reached 23 Oct 2026.
Category Code Search and Documentation
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 Security83
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token. See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- 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 Usability60
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 547 tokens (~273/item across 2 items; 2 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 Management23
- Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 3 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
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.
- 22 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 20 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 0
- Stability: unverified → 0.03 ▲ functional
- 16 Oct 26 +39
- Transport: unverified → pass ▲ security
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Authorization: Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token. security
- MCP protocol: unverified → pass ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Schema quality: good functional
- First check of Tool coverage: 100 functional
- First check of Tool coverage: 100 functional
- 14 Oct 26 33
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 23 Oct 2026 · Probed https://agent-docs-mcp.onrender.com/mcp/
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=onrender.com | CN=WE1,O=Google Trust Services,C=US | 21 Sept 2026 | 20 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | 6eb1e3fe7d0631ea1337bfa4a321c137 |
| SANs: onrender.com, *.onrender.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of agent-docs-mcp.onrender.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| onrender.com. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Challenged, unverified
The endpoint asked for a token, but we could not retrieve and validate the RFC 9728 metadata that tells a client how to obtain one.
| Result | Challenged, unverified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer
BearerProtected resource metadata
| Retrieved | No |
|---|---|
| Problem | no_resource_metadata |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://agent-docs-mcp.onrender.com/mcp/ | Verified | 200 | |
| http (plaintext) | http://agent-docs-mcp.onrender.com/mcp/ | HTTPS enforced | 301 | https://agent-docs-mcp.onrender.com/mcp/ |
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 →
read_section Read a section of an agent doc page ~205
Read a page found by search_docs. Without a heading: the page's description and outline (top-level sections with subsection counts). With a heading: that section's full text, including its subsections; continue long sections with next_offset. outline_depth=3 also lists subsections; use it only on long pages to find one specific subsection.
| Name | Type | Req | Description |
|---|---|---|---|
| heading | – | – | Heading to read, as listed in the outline (leading #s optional). Exact text first, case-insensitive, then a unique partial match; use 'Parent > Heading' when two headings share a name. Leave unset to… |
| offset | integer | – | Character offset into the section; pass the previous next_offset to continue a long section. |
| outline_depth | integer | – | Outline depth when no heading is given: 2 lists top-level sections with subsection counts, 3 also lists the subsections. |
| url | string | yes | Page URL exactly as search_docs returned it. |
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | yes | One sentence on what the page is. |
| heading | – | yes | Path of the section returned, e.g. 'Hooks > PreToolUse'; null when only the outline was asked for. |
| next_offset | – | yes | Pass as offset to read the rest; null when nothing is left. |
| offset | integer | yes | Offset of `text` within the section. |
| outline | array | yes | Top-level sections as '## Text (N subsections)' when no heading was asked for (at most 40 lines, then '+N more sections'); empty otherwise. |
| text | string | yes | Section markdown from its heading to the next heading of the same or higher level, at most 8,000 characters per call. |
| title | string | yes | Page title. |
| total_chars | integer | yes | Length of the whole section. |
| url | string | yes | Page URL. |
No examples provided.
search_docs Search official agent docs ~295
Search the official documentation of Claude Code, Cursor, OpenAI Codex and MCP. Use it before answering any question about using, configuring or administering these products. Not for other products or general programming. If the answer could differ between products and the user hasn't said which one, ask. Returns one passage per page, with the page's one-line description and a relevance score; under ~0.5 means the docs probably don't cover it. One topic per call: split multi-part questions. Need more than the passage? Call read_section(url), or read_section(url, heading) for one of the passage's other_sections.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Pages to return, 1-20 (default 8). |
| product | – | – | Only this product. Set it when the user has named the product, now or earlier in the conversation. Otherwise leave it empty: an unfiltered search still finds product-specific pages, while a wrong pro… |
| query | string | yes | What to find, in English: keywords or a short question, e.g. "<product> <feature> <what you need>". |
| response_format | string | – | `concise` (default): first 300 characters of each passage, enough to choose. `detailed`: full passages, about 800 tokens each. Start concise; re-run detailed with a small limit for the pages you need. |
| Name | Type | Req | Description |
|---|---|---|---|
| index_snapshot | – | yes | Date the documentation was indexed (ISO); null if unknown. |
| passages | array | yes | Ranked documentation passages. Empty if nothing matched. |
No examples provided.
How do I install the Agent Docs MCP server?
Agent Docs is a hosted endpoint at https://agent-docs-mcp.onrender.com/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 · agent-docs-mcp.onrender.com
claude mcp add --transport http konstantinstarovoytov-agent-docs 'https://agent-docs-mcp.onrender.com/mcp/'
What is the Agent Docs MCP server?
Agent Docs is an MCP server listed in the public MCP registry as io.github.KonstantinStarovoytov/agent-docs. Search the official docs of Claude Code, Cursor, OpenAI Codex and MCP, refreshed daily. This page covers its hosted endpoint (https://agent-docs-mcp.onrender.com/mcp/).
Is the Agent Docs MCP server safe to use?
Agent Docs scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Agent Docs MCP server expose?
Agent Docs exposes 2 tools: search_docs, read_section. Their descriptions and schemas cost roughly 500 tokens of context every time the server is loaded.
Does the Agent Docs MCP server require authentication?
Yes. Agent Docs asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Agent Docs MCP server still maintained?
Agent Docs is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.