"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 AI agents to manage plain .jsonl files as tables, offering tools to list libraries and tables, query data, and upsert rows while preserving byte-for-byte fidelity on unchanged rows.

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.

This server enables decidable, hardware-attested semantic verification of AI outputs using on-chip ballistic walks, providing reproducible receipts that can be recomputed byte-for-byte.

Enables safe, confirmable Proxmox operations: read-only cluster/guest status and bounded power actions and snapshot creation, with explicit byte-for-byte approval for each mutation.

Local, read-only MCP server that provides verified access to bounded.tools' signed static API, including the Web-Build Conformance report and SPDX SBOM, with byte-for-byte verification against a Sigstore-signed manifest.

Captures checkpoints of project files and SQLite tables before an AI agent makes risky changes, then reports differences and rolls them back byte-for-byte, including dropped tables and agent-created junk. Enables agents to snapshot, diff, list, and restore working state with explicit confirmation required before any destructive action.

Enables AI agents to validate .tdc configs, generate deterministic test data files locally, locate language and country data packs, summarise generated files, and read the TDCv2 docs as MCP tools. Everything runs on the user's machine, producing identical output byte for byte on every run.

Enables any MCP client to drive a retrieval-grounded multi-agent workflow over stdio JSON-RPC, with journalled effects so recorded runs replay byte-for-byte from their trace. It also lets an agent answer retrieval by calling a tool on another MCP server.

Captures an agentic asset's foundational record as a single asset-record.json, including creation facts and author-only confirmed metadata. Provides MCP tools to record, read, and finalize provenance during asset development.

Enables AI agents to run WP-CLI commands on WordPress sites, including byte-faithful post and meta copying with checksum verification, over local Docker, Pantheon Terminus, or SSH.

A code review tool that generates detailed HTML review documents by comparing branches or commits, with author filtering and intelligent analysis.

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.

MCP server for on-disk patching of binary artifacts with SHA-256 manifest, byte-level patch application, and manifest-driven restore, ensuring auditability and reversibility.

Enables validation of commit messages, branch names, author info, push safety, and repository state using commit-check rules, accessible as MCP tools.

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.

Enables AI agents to author node-graph-based procedural graphics as data and render them deterministically via a pinned headless engine, returning validated, hashed image artifacts with full provenance.

Enables AI agents to read and edit Word (.docx) and PDF documents with byte-level fidelity, using minimal in-package rewrites for DOCX and text-layer detection with page rendering for PDF, including OCR-free handling of scanned files via image output.

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.

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 AI agents to convert Markdown documents and multi-file books into PDFs, recover Markdown from PDFs that embed their source, and open notes in a live preview GUI, all without a browser, LaTeX, or Pandoc. Each conversion returns the PDF plus page count and rendering diagnostics, and produces byte-identical output on every run.

Exposes a set of honesty SDK TypeScript libraries as MCP tools so a coding agent can check grounded citations, corroborate evidence, test payout and mutation invariance, score trust and anonymous authenticity, validate provenance claims, track a claims registry and tamper-evident audit chain, and grade recommendations against outcomes. It also scaffolds two runtime kits for agent authorization receipts and pre-call cost governance.

Enables AI assistants to author, debug, and run Snowfakery data generation recipes through the Model Context Protocol.

Scans prompts for PII and masks or redacts sensitive data locally before sending to an LLM, supporting multiple anonymization modes.

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

Enables AI assistants to read and analyze Medium blog posts, including member-only content with login support, and search articles by author or keyword.

Enables AI assistants to work with local .ics calendar files over MCP, including agenda and search, free-time and conflict detection, DST-correct recurrence, and byte-preserving safe edits without accounts or network access.

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.