"author:0rkz/byte-mcp-server" matching MCP servers:

MCP server for lossless YAML 1.2 editing by AI agents. Two tools — noyalib_get (read a value at a dotted/indexed path) and noyalib_set (write a value, preserving comments/formatting byte-for-byte). Pure Rust, streaming-first serde, JSON Schema validation. MIT OR Apache-2.0.

Enables MCP-compatible agents to retrieve predictive port congestion signals, including congestion scores, ETA delays, waiting vessels, and freight volatility for supported ports, allowing supply chain risk assessment and informed decision-making.

Per-byte data marketplace for AI agents on Arbitrum. Discover publishers, evaluate on-chain Proof-of-Quality Score (PQS), subscribe + pay per request in USDC via the x402 gateway. 13 tools, no API keys, live testnet.

Verbatim context compaction for coding agents. Moves spent tool outputs to a local hash-checked stash the agent can recall, keeps every message byte for byte, and writes a JSON report of each cut. Offline, no API key. Tools: compact, compact_transcript, recall, inspect, prepare, explain, intake.

Enables AI coding agents to record and resume engineering work as durable, byte-exact threads of focus, decisions, evidence, and next steps.

Enables AI agents to convert PDF, Word, PowerPoint, Excel, HTML, EPUB, Outlook messages and web pages into Markdown for LLM and RAG workflows. Runs over stdio or HTTP and reproduces Microsoft markitdown's output byte for byte without a Python environment.

Enables searching Threads for specified keywords and returning deduplicated posts with author, date, likes, replies, and links, with age, like, and reply filters plus new-post tracking for scheduled runs.

Lets AI agents estimate the cost and result size of BigQuery and Snowflake queries before they run, then execute them only within per-call byte, row, and dollar bounds. Estimates are labeled with an accuracy tier so agents never over-trust an approximate figure.

Web search, crawling and ranking evaluation on your own YaCy peer: no API key, no central service. Results carry author-signature verdicts and declared tags.

Furl folds repeated tool output into a hash-addressed marker, keeps the line that matters, and returns any original byte-exact the moment the agent asks for it. No summary. No guessing. Nothing thrown away.

Enables AI agents to query Trino and Apache Pinot lakehouses under enforced governance, where every SQL statement is AST-validated, table-allowlisted, priced from the engine's own plan before it runs, and blocked or admitted against scan-byte and intermediate-row budgets. It also grounds agents with schema discovery tools, returns verified results with warnings instead of misleading answers, and records every tool call on an audit trail.

Author, validate, preview, and render motion-graphics videos from a single JSON document (Clipkit Protocol). 16 tools with in-chat PNG previews, captions, templated promos, and hand-off to a free browser editor by link.

AST-targeted code editing MCP server with 28 surgical tools for structural edits across 11 languages. Built on tree-sitter, replaces brittle search/replace with byte-correct edits keyed by symbol names.

MCP server for querying the Bibliothèque nationale de France catalogue. Enables searching authors and works, retrieving author details, listing editions, and finding digitised documents via SPARQL, without an API key.

Enables users to turn beats or topics into a ready media list by finding recent news articles, reading their bylines, and returning one row per journalist with name, outlet, author page, article count, latest article, and proof links. Runs the work on Apify and supports filters for date range, country, language, outlet domains, and minimum article counts.

Enables coding agents to author, validate, deploy, run, and observe automation workflows as Cloudflare Workers in the user's own Cloudflare account, with browser approval and secret-safe connection setup.

On-chain delivery receipts for x402 AI-agent payments on Solana: anchors SHA-256 digests of delivered content to a PDA after settlement; buyers verify proof of delivery offline with zero trust in the seller. Live MCP endpoint + npm bridge.

Verum's MCP server turns any codebase into a deterministic, queryable fact layer — an agent can ask who calls a function, what a change impacts, where the dead code and duplicates are, which client calls hit which routes, and run a full security/quality audit. It returns byte-identical answers in a few hundred tokens instead of grepping and reading whole files.

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

Enables inspection and verification of X.509 certificates and chains, CRLs, OCSP responses, CMS signatures and RFC 3161 timestamps, along with issuing certificates and CSRs, decoding ASN.1/PEM/OIDs, and opening PKCS#8 and PKCS#12 files without ever returning a key byte. Runs entirely offline with no network access, exposing 34 tools to any MCP client.

Test management over MCP: author test cases, run manual executions with per-case results, cut releases, and link automated tests to the cases they cover. Works against the hosted M00N Report service or a self-hosted instance.

Enables retrieval of public stats for TikTok video and photo posts by URL or post ID, returning one flat row per post with plays, likes, comments, shares, saves, caption, hashtags, post date, sound, and author follower and like totals. All work runs on an Apify actor, so the package acts as a thin client that starts the run and returns the dataset rows.

A pure-Python MCP server providing local byte-wrangling utilities including encoding, hashing, number conversion, and Ethereum primitives, with no network calls required.

diagramzu-mcp lets an AI client (Claude, Cursor, ChatGPT, etc.) author Mermaid diagrams in a shared workspace that a team can read, comment on, embed, and present at a clean URL — rather than just generating a one-off diagram. Hosted endpoint https://mcp.diagramzu.ai/mcp or local npx -y @diagramzu/mcp. Also listed in the official MCP registry as ai.diagramzu/mcp.

RSigma is a Rust detection-engineering toolkit for the Sigma standard. Its MCP server (rsigma mcp serve) exposes the toolchain to AI agents over stdio or Streamable HTTP, with tools to author, lint, validate, and convert Sigma rules, evaluate and explain detections against log events, and inspect correlation state.

Enables AI agents to turn live web pages or supplied HTML into clean, main-content Markdown with title, author, date and language metadata. It respects robots.txt and AI opt-outs, reporting refusal reasons, quota, and plain-language errors back to the agent.

Enables auditing URLs for AI crawler readiness, including 25,000-token RAG truncation, /llms.txt discovery, Lighthouse 13.5 ard-schema compliance, and JSON-LD entities, plus generating manifests and clean Byte-0 Markdown inside MCP clients.

Enables agents to author, validate, inspect, patch, and render editable JSON pixel-art and animation recipes through local tools, producing PNG contact sheets, APNGs, sprite atlases, and related export bundles.

Checks whether a coding agent's fix is really guarded by a test: check_fix takes the latest change back out of a copy of the project, runs its tests, and says whether any test noticed; ask_bite does the same for past fixes. Free, no API key.

MCP server for MDMA (Markdown Document with Mounted Applications) — interactive Markdown with forms, approval gates, tables, and more. Exposes the MDMA spec, authoring prompts, package metadata, and live docs to AI assistants so agents can author and integrate MDMA correctly.