// SCAN REPORT

Entroly Context Engine

52 tools. 24 can modify or destroy data without limits.

21 write tools that can modify data. Rate limits recommended.

Last updated: 10 Jun 2026

24 can modify or destroy data

28 read-only

52 tools total

Community server · catalogue entry verified 10/06/2026

How to control Entroly Context Engine ↓

TOOL MAP

What Entroly Context Engine exposes to your agents

Read (28) Write / Execute (21) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Entroly Context Engine tools

Execute · High execute_flow This tool executes arbitrary workflows end-to-end with automatic chaining and action triggering. Execute · High start_workspace_listener This tool launches a daemon/background process that monitors repository activity and automatically feeds events into downstream systems (CogOps/Belief CI). Execute · Medium manage_skills The 'benchmark' action runs test cases (code execution), and 'promote/prune' actions modify or remove skill objects in the system lifecycle. Execute · Medium epistemic_route This tool executes a routing/orchestration operation that inspects signals and triggers downstream flows (Belief → Action, Verification → Action, etc.).

24 of Entroly Context Engine's 52 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Entroly Context Engine

PolicyLayer is an MCP gateway — it sits between your AI agents and Entroly Context Engine, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "compile_docs": {
    "limits": [
      {
        "counter": "compile_docs_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "compile_beliefs": {
    "limits": [
      {
        "counter": "compile_beliefs_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Entroly Context Engine — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ENTROLY CONTEXT ENGINE →

Free to start. No card required.

FULL CATALOGUE

All 52 Entroly Context Engine tools

EXECUTE 5 tools

Execute execute_flow Execute a full canonical epistemic flow end-to-end. Routes the query through the Epistemic Ingress Co Execute start_workspace_listener Start a background workspace listener that continuously feeds repo changes into CogOps. This is the l Execute epistemic_route Route a query through the CogOps Epistemic Ingress Controller. Inspects 4 signals (intent, belief cov Execute process_change Process a code change through the Change-Driven pipeline (Flow ④). Full pipeline: Diff → ChangeSet → Execute manage_skills Manage the CogOps skill lifecycle (Evolution layer). Actions: - list: Show all skills with st

WRITE 16 tools

Write compile_docs Compile markdown documentation files into belief artifacts. Ingests project-level docs (README.md, AR Write ingest_diagram Ingest an architecture or flow diagram into the context memory. Converts Mermaid, PlantUML, DOT/Graph Write ingest_voice Ingest a voice/meeting transcript into the context memory. Converts pre-transcribed text (from Whispe Write record_ci_result record_ci_result Write record_outcome Record whether selected fragments led to a successful output. This feeds the reinforcement learning l Write record_test_result record_test_result Write refresh_beliefs Mark beliefs as stale after file changes (Flow ④ doc-refresh). Given changed files, finds related bel Write remember_fragment Store a context fragment with automatic dedup and entropy scoring. Fragments are fingerprinted via Si Write sync_workspace_changes Synchronize workspace file changes into the belief and verification layers. Detects new, modified, an Write checkpoint_state Save current state to disk for crash recovery and session resume. Checkpoints include all fragments, Write create_context_receipt Create a Context Receipt from supplied documents. documents_json may be: - a JSON object mapp Write create_skill Create a new skill from a capability gap (Evolution layer). When the system repeatedly fails on a top Write export_training_data Export vault beliefs as JSONL training data for LLM finetuning. Generates instruction-following pairs Write record_edit_outcome record_edit_outcome Write vault_write_action Write a task output or report to the CogOps Knowledge Vault. Action artifacts are developer-facing ou Write vault_write_belief Write a belief artifact to the CogOps Knowledge Vault. Beliefs are durable system understanding — wha

READ 28 tools

Read compile_beliefs Compile source code into belief artifacts (Truth → Belief pipeline). Scans a directory for source fil Read analyze_codebase_health Analyze the health of the ingested codebase. Runs 5 analysis passes over all fragments in the current Read blast_radius Analyze the blast radius of file changes on existing beliefs. Given a list of changed files, determin Read coverage_gaps Find source files with no corresponding belief in the vault. Scans a directory for source files (.py, Read eicv_verify_claim eicv_verify_claim Read entroly_dashboard Show the real, live value Entroly is providing to YOUR session right now. Pulls from actual engine st Read entroly_retrieve Retrieve exact source content omitted by compressed context. Use the retrieval handle attached to a s Read explain_context Explain why each fragment was included or excluded in the last optimization. Shows per-fragment scori Read explain_receipt_omission Explain why a chunk was omitted from a Context Receipt. Read get_stats Get comprehensive session statistics. Shows token savings, duplicate detection counts, entropy Read ingest_diff Ingest a code diff/patch into the context memory. Converts a unified diff (git diff output) into a st Read prefetch_related Predict and pre-load context that will likely be needed next. Combines static analysis (imports, call Read recall_relevant Semantic recall of the most relevant stored fragments. Uses SimHash fingerprint distance + multi-dime Read render_context_receipt Render a Context Receipt JSON artifact as a Markdown report. Read repo_file_map Return the canonical Entroly file map across the Python, Rust core, and WASM repos. Use this to under Read scan_for_vulnerabilities scan_for_vulnerabilities Read security_report Generate a session-wide security audit across all ingested fragments. Scans every fragment in the cur Read security_scan security_scan Read smart_read Read a file with automatic resolution optimization. Instead of choosing between full/map/signatures m Read vault_query Query the CogOps Knowledge Vault for existing beliefs. Use this to check what the system already know Read vault_search vault_search Read vault_status Show the current state of the CogOps Knowledge Vault. Initializes the vault directory structure if ne Read verify_and_repair Verify LLM-generated code and suggest repairs for hallucinations. Combines BIPT verification with rej Read verify_beliefs Run a full verification pass on all beliefs in the vault. Checks for: - Staleness (beliefs pa Read verify_provenance Verify that LLM-generated code is grounded in the provided context. Uses BIPT (Byte-level Information Read verify_response verify_response Read create_context_receipt_from_path Create a Context Receipt from a local document file or directory. Supports text-like documents curren Read resume_state Resume from the latest checkpoint. Restores all context fragments, dedup index, co-access patterns,

OTHER 3 tools

Other eicv_suppress_hallucinations eicv_suppress_hallucinations Other optimize_context optimize_context Other record_command_exit record_command_exit

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Entroly Context Engine

How do I prevent bulk modifications through Entroly Context Engine? +

The Entroly Context Engine server has 16 write tools including compile_docs, ingest_diagram, ingest_voice. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Entroly Context Engine.

How many tools does the Entroly Context Engine MCP server expose? +

52 tools across 3 categories: Execute, Read, Write. 28 are read-only. 24 can modify, create, or delete data.

How do I enforce a policy on Entroly Context Engine? +

Register the Entroly Context Engine MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Entroly Context Engine tool call.

Deterministic rules across all 52 Entroly Context Engine tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ENTROLY CONTEXT ENGINE →

Free to start. No card required.

52 Entroly Context Engine tools catalogued and risk-classified — across an index of 43,000+ MCP servers.