Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

redcon

PYPI · REDCON

Deterministic context packing for AI coding agents; measured 83% fewer input tokens, local.

Available components

+15 this week 90 Trust /100

Last scanned (4 hours ago)

Scores higher than 93% of PyPI servers

Category Developer Tools

Trust breakdown (7 categories)

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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency87
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to natiixnt/redcon). View diagnostics → Pass
  • Licence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.Unverified
  • Actively maintained (last published 82 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability68
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1234 tokens (~137/item across 9 items; 9 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage83
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 50% 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 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
Changelog

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.

  • 5 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 4 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 3 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 1 Nov 26 0
    • Stability: 0.97 → pass security
  • 31 Oct 26 0
    • Stability: pass → 0.97 functional
  • 26 Oct 26 −15
    • Malware scan: pass → unverified ▼ security
  • 25 Oct 26 0
    • Stability: 0.97 → pass security
  • 24 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

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 5 Nov 2026 · Analysed pypi/redcon@1.15.0

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 pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo natiixnt/redcon
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/natiixnt/redcon/.github/workflows/release.yml@refs/tags/v1.15.0
Rekor log index 2336881586
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:8db3d156a57c466a2d35c466a831d4394a4f9f9d8c5a70cd6c7511fa53acb7ae

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 9 exposed · ~1,234 tokens

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 →

Tool Tokens
redcon_budget ~107

Plan how to fit a set of files into a token budget, choosing a compression strategy per file. Use BEFORE reading several files at once, whenever their combined size could blow the context: returns per-file token costs, chosen strategies, and which files must be dropped to stay under the budget.

NameTypeReqDescription
filesarrayyesRelative paths of files to fit
max_tokensintegeryesTotal token budget
repostring––
taskstringyesTask description

No output schema declared.

No examples provided.

redcon_compress ~111

Task-scoped compressed view of one file: signatures, imports and the sections relevant to the task, typically 3-10x fewer tokens than the raw file. Default to this INSTEAD of reading a whole file; fetch the full file only if the compressed view turns out to be insufficient.

NameTypeReqDescription
max_tokensinteger–Max tokens for compressed output
pathstringyesRelative path to the file
repostring––
taskstringyesTask description

No output schema declared.

No examples provided.

redcon_overview ~84

Lightweight repository map grouped by directory, filtered to modules relevant to the task. Use when orienting in an unfamiliar repo instead of ls -R, find, or reading READMEs; costs a few hundred tokens. For actual code structure (signatures), use redcon_repo_map instead.

NameTypeReqDescription
repostring––
taskstringyesTask description

No output schema declared.

No examples provided.

redcon_quality_check ~126

Run a shell command, compress its output, and verify the compression against the M8 quality harness (must-preserve patterns, reduction floor, determinism). Use this instead of redcon_run when you want a verdict before consuming the compressed bytes - the response is small and the verdict is structured.

NameTypeReqDescription
commandstringyes–
cwdstring––
max_output_tokensinteger––
prefer_compact_outputboolean––
quality_floorstring––
remaining_tokensinteger––
timeout_secondsinteger––

No output schema declared.

No examples provided.

redcon_rank ~121

Rank repository files by relevance to a task using keyword and import-graph signals. Call this FIRST on any new task, before searching or reading files: it replaces guessing paths, broad grep sweeps, and directory listings. Returns the top-K paths with scores and reasons; follow up with redcon_compress on the top hits instead of reading them whole.

NameTypeReqDescription
repostring–Repository path (default: current directory)
taskstringyesDescription of what you're working on
top_kinteger–Number of top files to return

No output schema declared.

No examples provided.

redcon_repo_map ~121

Repo map: top ranked files plus their class/function signatures with line numbers, fitted under a token budget. Use when you need code structure across many files at once - one call replaces opening files one by one to learn their shape. Unlike redcon_overview it emits actual signatures, not just paths. Degrades to a path-only listing when the redcon[symbols] extra is missing rather than failing.

NameTypeReqDescription
budgetinteger––
repostring––
taskstringyes–
top_filesinteger––

No output schema declared.

No examples provided.

redcon_run ~321

Run a shell command and return its output compressed for LLM consumption via schema-aware compressors (pytest, git diff/status/log, builds, coverage, kubectl and more). Use INSTEAD of a raw shell whenever output may exceed a screenful - test runs, diffs, logs. The token caps are hard guarantees, and failures keep their essential detail (failing test names, error lines). DISABLED by default because it executes commands; set REDCON_MCP_ENABLE_RUN=1 on the server to enable it.

NameTypeReqDescription
commandstringyesFull command line, e.g. 'git diff HEAD'
cwdstring–Working directory
max_output_tokensinteger–Hard cap on tokens returned
prefer_compact_outputboolean–Rewrite known commands to runner-native compact flags (pytest --tb=line, cargo --quiet, jest --reporter=basic) before spawning. Trades full tracebacks for ~60-80% upstream reduction on test-failure r…
quality_floorstring–Lowest acceptable detail level
remaining_tokensinteger–Remaining budget hint (drives compression aggressiveness)
semantic_fallbackboolean–Enable the LLMLingua-2 semantic compression fallback for commands that no schema-specific compressor recognised. Requires the optional redcon[heavy_compression] extra (torch + transformers + ~280 MB…
timeout_secondsinteger–Kill the command after this many seconds

No output schema declared.

No examples provided.

redcon_search ~123

Regex search over the repository. scope='ranked' (default) searches only the files relevant to the task, so matches come pre-filtered by relevance instead of drowning you in hits; scope='all' covers the whole repo. Prefer this over raw grep on large repositories.

NameTypeReqDescription
max_resultsinteger––
patternstringyesRegex pattern to search for
repostring––
scopestring––
taskstringyesTask description (used for scope='ranked')
top_kinteger––

No output schema declared.

No examples provided.

redcon_structural_search ~120

Search code by AST pattern (ast-grep), not regex. Patterns like `class $NAME { $$$ }` match real class declarations and skip text occurrences inside comments / strings. Available when ast-grep is on PATH or redcon[ast_grep] is installed; returns backend=unavailable otherwise so callers can fall back to redcon_search.

NameTypeReqDescription
languagestring–Language hint (python, javascript, rust, ...)
max_resultsinteger––
patternstringyes–
scopestring––

No output schema declared.

No examples provided.

Install

How do I install the redcon MCP server?

redcon runs locally as a PyPI package, launched with uvx redcon. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · redcon

# add to Claude Code
claude mcp add natiixnt-redcon -- uvx redcon
Common questions

What is the redcon MCP server?

redcon is an MCP server listed in the public MCP registry as io.github.natiixnt/redcon. Deterministic context packing for AI coding agents; measured 83% fewer input tokens, local. This page covers its PyPI package (redcon).

Is the redcon MCP server safe to use?

redcon scores 90 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. 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 redcon MCP server expose?

redcon exposes 9 tools: redcon_rank, redcon_overview, redcon_compress, redcon_search, redcon_budget, and 4 more. Their descriptions and schemas cost roughly 1,234 tokens of context every time the server is loaded.

Is the redcon MCP server still maintained?

redcon is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.