llms.txt
OCI · GHCR.IO/BASITALISANDHU/MCP-LLMS-TXT
Build llms.txt from local Markdown or a sitemap.xml and check an existing llms.txt file.
Available components
Last scanned (13 minutes ago)
Scores higher than 74% of OCI servers
Category Code Search and Documentation
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to basitalisandhu/dev-mcp-servers). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 3 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability59
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 656 tokens (~218/item across 3 items; 3 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 Management10
- Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage81
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 42% 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 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
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.
- 17 Oct 26 +2
- Stability: unverified → 0.10 ▲ functional
- 14 Oct 26 +27
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Tool coverage: 42 functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Schema quality: good functional
- 13 Oct 26 0
- Package version: 0.2.0 → 0.2.1 functional
- 12 Oct 26 0
- Package version: 0.1.1 → 0.2.0 functional
- 7 Oct 26 20
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 17 Oct 2026 · Analysed oci/ghcr.io/basitalisandhu/mcp-llms-txt@0.2.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | oci |
| Reason | Verified |
| Discovered via | OCI referrers API |
| Source repo | basitalisandhu/dev-mcp-servers |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/basitalisandhu/dev-mcp-servers/.github/workflows/publish-github-packages.yml@refs/tags/v0.2.1 |
| Rekor log index | 3244679805 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha256:c3a61cd8563d2df826c876a86d942c5f1c81dcd78f61b870cebd2a40191bc52f |
Background: How many MCP packages publish verified provenance →
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 →
check_llms_txt Check an llms.txt file ~110
Validate llms.txt text (from a local path or inline content) against the convention: exactly one H1 first, an optional blockquote summary, H2 sections containing only '- [name](url): notes' items, no deeper headings, no duplicate URLs or sections, a modest size. Returns errors (convention violations), warnings, info (such as links without notes or relative URLs) with line numbers, and statistics.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | – | – |
| path | string | – | – |
No output schema declared.
No examples provided.
generate_from_sitemap Generate llms.txt from a local sitemap.xml ~169
Read a sitemap.xml from a local path (download it first; this tool does not fetch URLs) and return an llms.txt with one link per <url>, grouped into sections by the first path segment. Titles are derived from the last path segment because page content is not fetched, so notes are empty; edit them afterwards. include_prefix and exclude_prefix filter by URL path. Child sitemaps in a sitemap index are listed but not read.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | – |
| details | string | – | – |
| exclude_prefix | array | – | – |
| include_prefix | array | – | – |
| max_urls | integer | – | Default 1000. |
| optional_sections | array | – | – |
| path | string | yes | Local path to sitemap.xml. |
| title | string | yes | – |
No output schema declared.
No examples provided.
generate_llms_txt Generate llms.txt from Markdown ~280
Scan a local directory (recursively, skipping node_modules, .git, build output and hidden directories, up to max_files files) for .md, .mdx and .markdown files and return an llms.txt. Each file's title comes from frontmatter, its first H1 or the file name; its notes from frontmatter description or the first paragraph (trimmed to 200 characters). Files are grouped into sections by top-level folder (root files under Docs). URLs are base_url plus the relative path, with .md stripped and README/index mapped to the folder unless url_style is keep-extension. Sections named in optional_sections are moved under Optional. Returns the text, the entries, and anything skipped.
| Name | Type | Req | Description |
|---|---|---|---|
| base_url | string | – | Prefix for links, for example https://docs.example.com. Default: root-relative paths. |
| description | string | – | One-sentence summary for the blockquote. |
| details | string | – | Optional paragraph(s) placed after the summary. |
| directory | string | yes | – |
| include_dirs | array | – | Only scan these top-level directories (use "." to keep root files). |
| max_files | integer | – | Default 1000. |
| optional_sections | array | – | – |
| title | string | yes | H1 title, usually the project name. |
| url_style | string | – | – |
No output schema declared.
No examples provided.
How do I install the llms.txt MCP server?
llms.txt runs locally as a container image, launched with docker run --rm -i ghcr.io/basitalisandhu/mcp-llms-txt:0.2.1. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/basitalisandhu/mcp-llms-txt
claude mcp add basitalisandhu-mcp-llms-txt -- docker run --rm -i ghcr.io/basitalisandhu/mcp-llms-txt:0.2.1
What is the llms.txt MCP server?
llms.txt is an MCP server listed in the public MCP registry as io.github.basitalisandhu/mcp-llms-txt. Build llms.txt from local Markdown or a sitemap.xml and check an existing llms.txt file. This page covers its container image (ghcr.io/basitalisandhu/mcp-llms-txt).
Is the llms.txt MCP server safe to use?
llms.txt scores 49 out of 100 on VerifyMCP. Its build provenance is signed and verified. 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 llms.txt MCP server expose?
llms.txt exposes 3 tools: generate_llms_txt, generate_from_sitemap, check_llms_txt. Their descriptions and schemas cost roughly 559 tokens of context every time the server is loaded.
Is the llms.txt MCP server still maintained?
llms.txt is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the llms.txt MCP server under?
llms.txt declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.