Mmcp.market

Entroly MCP server

by juyterman1000·io.github.juyterman1000/entroly·v1.0.84

Context Assurance for AI agents: context engineering, AI cost optimization, verification.

B77/100grade B
What users say
No reviews yet
Be the first
Safety scan
B77/100

full report

Adoption
Established

460 stars371 downloads/wk

Reviews

Write one

Nobody has reviewed Entroly yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Entroly tools (100, 12 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • advance_proof_guided_context

    Verify one model round and return exact evidence or a final answer.

  • analyze_codebase_health

    Analyze the health of the ingested codebase.

  • blast_radius

    Analyze the blast radius of file changes on existing beliefs.

  • checkpoint_state

    Save state plus explicit decisions needed for safe continuation.

  • compile_beliefs

    Compile source code into belief artifacts (Truth → Belief pipeline).

  • compile_docs

    Compile markdown documentation files into belief artifacts.

  • compress_image

    Compress an image for vision model input, with optional OCR text extraction.

  • compress_shell

    Compress CLI output (git, npm, cargo, pytest, etc.) preserving errors and key info.

  • coverage_gaps

    Find source files with no corresponding belief in the vault.

  • create_context_receiptwrite action

    Create a Context Receipt from supplied documents.

  • create_context_receipt_from_pathwrite action

    Create a Context Receipt from a local document file or directory.

  • create_skillwrite action

    Create a new skill from a capability gap (Evolution layer).

  • eicv_suppress_hallucinations

    Verify an LLM response and optionally rewrite hallucinated claims.

  • eicv_verify_claim

    Verify a single claim against evidence using the EICV pipeline.

  • entroly_dashboard

    Show the real, live value Entroly is providing to YOUR session right now.

  • entroly_retrieve

    Retrieve exact source content omitted by compressed context.

  • epistemic_route

    Route a query through the CogOps Epistemic Ingress Controller.

  • execute_flowwrite action

    Execute a full canonical epistemic flow end-to-end.

  • explain_context

    Explain why each fragment was included or excluded in the last optimization.

  • explain_receipt_omission

    Explain why a chunk was omitted from a Context Receipt.

  • export_training_data

    Export vault beliefs as JSONL training data for LLM finetuning.

  • get_stats

    Get comprehensive session statistics.

  • ingest_diagram

    Ingest an architecture or flow diagram into the context memory.

  • ingest_diff

    Ingest a code diff/patch into the context memory.

  • ingest_voice

    Ingest a voice/meeting transcript into the context memory.

  • inspect_proof_guided_context

    Inspect the last durable proof-guided response without advancing it.

  • learn_from_failures

    Mine failure patterns from PRISM, vault, and evolution data. Optionally apply corrections.

  • list_compression_receipts

    List only receipts visible to this workspace/session scope.

  • manage_skills

    Manage the CogOps skill lifecycle (Evolution layer).

  • optimize_context

    Select a high-value context subset for a token budget.

  • prefetch_related

    Predict and pre-load context that will likely be needed next.

  • prepare_proof_guided_context

    Prepare a durable proof-guided model request from local documents.

  • prepare_task_dream

    Prepare an expiring, receipt-backed task skill before agent work.

  • process_change

    Process a code change through the Change-Driven pipeline (Flow ④).

  • recall_relevant

    Semantic recall of the most relevant stored fragments.

  • record_ci_result

    Record CI pipeline pass/fail status for a request.

  • record_command_exit

    Record the exit code of a command that was generated and executed.

  • record_edit_outcome

    Record whether the user accepted, reverted, or retried an AI edit.

  • record_outcome

    Record whether selected fragments led to a successful output.

  • record_test_result

    Record that tests RAN and either passed or failed for a request.

  • recover_receipt_omission

    Recover the full text of context a Context Receipt omitted.

  • recover_shell

    Recover full CLI output from a compression handle.

  • refresh_beliefs

    Mark beliefs as stale after file changes (Flow ④ doc-refresh).

  • refresh_repository_index

    Atomically rebuild the fixed repository snapshot.

  • remember_fragment

    Store a context fragment with automatic dedup and entropy scoring.

  • render_context_receipt

    Render a Context Receipt JSON artifact as a Markdown report.

  • repo_file_map

    Return the canonical Entroly file map across the Python, Rust core, and WASM repos.

  • repository_architecture

    Return verified layers, communities, cycles, routes, and hotspots.

  • repository_architecture_diff

    Compare two committed architecture receipts and report structural drift.

  • repository_change_impact

    Return reverse file/call impact for known workspace-relative paths.

  • repository_code_health

    Audit verified complexity, cycles, coupling, and navigability risk.

  • repository_file_move_apply

    Apply a blocker-free module move after commitment and risk checks.

  • repository_file_move_preview

    Preview a headless Python module move with exact import rewrites.

  • repository_git_architecture_diff

    Compare a local Git commit with the verified worktree without checkout.

  • repository_graph_query

    Query verified typed neighbors, paths, relatedness, or impact.

  • repository_graph_snapshot

    Export the complete bounded graph as a portable committed snapshot.

  • repository_graph_snapshot_check

    Verify a shared snapshot and prove whether it matches current sources.

  • repository_http_routes

    Discover verified HTTP routes, mounted prefixes, handlers, and collisions.

  • repository_interprocedural_flow

    Trace source-verified arguments, parameters, returns, and consumers.

  • repository_lsp_rename_previewwrite action

    Run the operator-configured LSP and return a committed no-write plan.

  • repository_map

    Rank a receipt-backed structural map across the fixed repository.

  • repository_program_graph

    Return verified Python control flow and reaching definitions.

  • repository_program_slice

    Build a proof-carrying partial code slice from verified facts.

  • repository_rename_apply

    Apply a previewed rename after plan-hash and risk acknowledgement.

  • repository_rename_preview

    Preview exact rename edits; performs no writes and reports incompleteness.

  • repository_runtime_overlay

    Bind value-free runtime events to fresh source and symbol evidence.

  • repository_safe_delete_applywrite action

    Apply a blocker-free delete after plan-hash and risk acknowledgement.

  • repository_safe_delete_previewwrite action

    Preview a headless delete; any known or lexical reference blocks it.

  • repository_semantic_overlay

    Verify external LSP/compiler ranges before trusting semantic edges.

  • repository_summary

    Return bounded counts and the deterministic repository-index digest.

  • repository_symbol_graph

    Trace freshness-checked static calls without guessing symbol identity.

  • repository_tests_for_changes

    Rank tests related to known changed paths without executing them.

  • repository_verified_context

    Return a partial code graph scoped to one task with a receipt.

  • resume_state

    Resume by task relevance; omit query only for latest-checkpoint behavior.

  • retrieve_compressed_span

    Retrieve one in-scope span and debit returned tokens from savings.

  • scan_for_vulnerabilities

    Scan code content for security vulnerabilities (SAST analysis).

  • search_compressed_spans

    Search in-scope spans and return bounded exact excerpts.

  • security_report

    Generate a session-wide security audit across all ingested fragments.

  • security_scan

    Scan content for prompt injection attacks and security threats.

  • shared_memory_forgetwrite action

    Remove a shared memory entry by ID.

  • shared_memory_list

    List shared memory entries, optionally filtered by agent or tag.

  • shared_memory_search

    Search cross-agent shared memory by relevance. Returns entries from all agents.

  • shared_memory_stats

    Get cross-agent shared memory statistics.

  • shared_memory_writewrite action

    Write to cross-agent shared memory. Deduplicates near-identical entries via SimHash.

  • smart_read
  • start_workspace_listener

    Start a background workspace listener that continuously feeds repo changes into CogOps.

  • steer_output

    Classify query effort and return output steering directives + max_tokens budget.

  • sync_workspace_changes

    Synchronize workspace file changes into the belief and verification layers.

  • vault_hygiene_scan

    Scan vault beliefs against each other for knowledge decay.

  • vault_query

    Query the CogOps Knowledge Vault for existing beliefs.

  • vault_search

    Full-text search across all belief artifacts in the vault.

  • vault_status

    Show the current state of the CogOps Knowledge Vault.

  • vault_time_travel

    Query the vault's bitemporal belief ledger — memory time travel.

  • vault_write_actionwrite action

    Write a task output or report to the CogOps Knowledge Vault.

  • vault_write_beliefwrite action

    Write a belief artifact to the CogOps Knowledge Vault.

  • verify_and_repair

    Verify LLM-generated code and suggest repairs for hallucinations.

  • verify_beliefswrite action

    Run a full verification pass on all beliefs in the vault.

  • verify_provenance

    Verify that LLM-generated code is grounded in the provided context.

  • verify_response

    Verify an AI-generated response for hallucination using the 4-signal fusion cascade.

  • work_state

    Inspect persisted shared work state without appending a polling event.

Public scan report

scanner v0.1.8 · 2026-09-19 · same rubric, same numbers if you re-run it

2 medium
  • Code scan494 source files scanned; 3 source files scanned15/25
  • Live reliabilityno gateway calls yet and no remote to proben/a
  • Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (2)

  • mediumsubprocess with shell=Trueexec.shell-true
    entroly-1.0.84/entroly/cli.py: …cutable # Never retry through ``shell=True``. ``agent_args`` are supplied by …
  • mediumeval / new Function usedexec.eval
    entroly-1.0.84/entroly/ravs/executors.py: …alidate_ast(tree) result = eval( # noqa: S307 compile(t…
Overall 77/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Entroly repository's README, as published. We do not edit it. Read it on GitHub

Entroly — Select AI context with auditable recovery.

Receipt-backed selection records: what was kept, what was omitted, and the handle that recovers the exact original bytes. Compression you can undo, on your own repository, in one command — without replacing your model or agent architecture.

code --install-extension entroly.entroly-vscode  ·  pip install -U entroly && entroly go  ·  npx entroly Entroly is an open-source, local-first AI token-efficiency and Context Assurance layer: budgeted evidence selection, recoverable context compression, content-addressed evidence recovery, and auditable receipts. Works through VS Code, Claude Code, Cursor, Codex, OpenClaw, GitHub Copilot, Aider, and OpenAI/Anthropic-compatible apps.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-09-19restoreDBscore 77: subprocess with shell=True; eval / new Function used

Install directly

claude mcp add entroly -- uvx entroly
Add to Cursor

Entroly: common questions

Is Entroly MCP server safe?
Mostly: it is graded B (77/100). Read the Entroly safety report
How do I install Entroly?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Entroly need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Entroly maintained?
The last commit was in the last day (2026-09-19). The latest release is v1.0.84.

More from juyterman1000