// SCAN REPORT

Vcon

19 tools. 6 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

6 can modify or destroy data

13 read-only

19 tools total

Community server · catalogue entry verified 29/06/2026

How to control Vcon ↓

TOOL MAP

What Vcon exposes to your agents

Read (13) Write / Execute (6) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Vcon tools

Execute · Medium siprec_ingest_file Manually trigger ingestion of a SIPREC XML or JSON file from the watch folder. Useful for testing or re-processing. Execute · Medium whatsapp_parse_preview Parse a WhatsApp chat export and return a preview without creating a vCon. Write · Medium teams_import_file Import a Teams call record JSON file and create a vCon. File must follow MS Graph callRecord schema. Write · Medium teams_import_folder Import all Teams call record JSON files from a folder. Defaults to the sample-data directory.

6 of Vcon's 19 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Vcon

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

Rate limit write operations

{
  "teams_import_file": {
    "limits": [
      {
        "counter": "teams_import_file_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ai_analyze_vcon": {
    "limits": [
      {
        "counter": "ai_analyze_vcon_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 Vcon — 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 VCON →

Instant setup, no code required.

FULL CATALOGUE

All 19 Vcon tools

EXECUTE 2 tools

Execute siprec_ingest_file Manually trigger ingestion of a SIPREC XML or JSON file from the watch folder. Useful for testing or re-proces Execute whatsapp_parse_preview Parse a WhatsApp chat export and return a preview without creating a vCon.

WRITE 4 tools

Write teams_import_file Import a Teams call record JSON file and create a vCon. File must follow MS Graph callRecord schema. Write teams_import_folder Import all Teams call record JSON files from a folder. Defaults to the sample-data directory. Write whatsapp_import_file Import a WhatsApp exported chat .txt file and create a vCon. Write whatsapp_import_folder Import all WhatsApp .txt files from a folder. Defaults to sample-data directory.

READ 13 tools

Read ai_analyze_vcon Run AI analysis (sentiment, summary, topics) on a specific vCon by UUID. Useful for re-analyzing or analyzing Read ai_analyzer_status Get AI analyzer status: sidecar connection, analysis count, model info. Read ai_query Ask a natural language question about conversations. Provide context chunks from vCon transcripts for RAG-styl Read jsonld_confidence_query Query confidence scores for a vCon. Returns per-party and per-analysis confidence with Subjective Logic opinio Read jsonld_get_enrichment Get the full JSON-LD-ex semantic enrichment for a vCon, including provenance annotations, confidence scores, i Read jsonld_provenance_chain Trace the full provenance chain for a vCon: who created it, what models analyzed it, confidence scores, integr Read jsonld_trust_propagation Compute trust propagation through an analysis chain using Subjective Logic. For example: transcript confidence Read jsonld_verify_integrity Verify the cryptographic integrity of a vCon enrichment. Returns whether the document has been tampered with s Read neo4j_insights Get pre-built graph insights: repeat_callers, topic_clusters, escalation_paths, contact_network, or graph_stat Read neo4j_query Run a read-only Cypher query against the vCon knowledge graph. Use for finding repeat callers, topic clusters, Read siprec_status Get SIPREC adapter status: watch folder path, pending files, processed count. Read teams_status Get Teams adapter status: watch folder, stats, connection info. Read whatsapp_status Get WhatsApp adapter status.

EXPLORE

Related servers

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

FAQ

Questions about Vcon

How do I prevent bulk modifications through Vcon? +

The Vcon server has 4 write tools including teams_import_file, teams_import_folder, whatsapp_import_file. 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 Vcon.

How many tools does the Vcon MCP server expose? +

19 tools across 3 categories: Execute, Read, Write. 13 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Vcon? +

Register the Vcon 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 Vcon tool call.

Deterministic rules across all 19 Vcon tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON VCON →

Instant setup, no code required.

19 Vcon tools catalogued and risk-classified — across an index of 43,000+ MCP servers.