New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

OpenTCM_Discovery

69 tools. 9 can modify or destroy data without limits.

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

Last updated:

9 can modify or destroy data
60 read-only
69 tools total

Community server · catalogue entry checked 14/10/2026

How to control OpenTCM_Discovery ↓

What OpenTCM_Discovery exposes to your agents

Read (60) Write / Execute (9) Destructive / Financial (0)
High Risk

The most dangerous OpenTCM_Discovery tools

9 of OpenTCM_Discovery's 69 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control OpenTCM_Discovery

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

Rate limit write operations
{
  "tcm_convert_dose": {
    "limits": [
      {
        "counter": "tcm_convert_dose_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "dock_analyze_contacts": {
    "limits": [
      {
        "counter": "dock_analyze_contacts_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register OpenTCM_Discovery — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON OPENTCM_DISCOVERY →

Instant setup, no code required.

All 69 OpenTCM_Discovery tools

READ 60 tools
Read dock_analyze_contacts dock_analyze_contacts Read dock_analyze_runtime dock_analyze_runtime Read dock_check_environment dock_check_environment Read dock_compare_experiments dock_compare_experiments Read dock_fetch_structure dock_fetch_structure Read dock_report_insight dock_report_insight Read tcm_adme_profile tcm_adme_profile Read tcm_admet_predict tcm_admet_predict Read tcm_align_tcmsp tcm_align_tcmsp Read tcm_analysis_topology tcm_analysis_topology Read tcm_analyze_runtime tcm_analyze_runtime Read tcm_audit_evidence tcm_audit_evidence Read tcm_broad_names 列出一味名称的本地候选。只调用已有的名称候选函数。 Read tcm_cache_status tcm_cache_status Read tcm_check_database_status tcm_check_database_status Read tcm_check_docking_replay tcm_check_docking_replay Read tcm_chembl_lookup tcm_chembl_lookup Read tcm_classify_structure tcm_classify_structure Read tcm_clean_table tcm_clean_table Read tcm_cross_database_screen tcm_cross_database_screen Read tcm_ctd_gene_interactions tcm_ctd_gene_interactions Read tcm_dependency_status tcm_dependency_status Read tcm_dgidb_interactions tcm_dgidb_interactions Read tcm_enrichment_analysis tcm_enrichment_analysis Read tcm_ensembl_lookup tcm_ensembl_lookup Read tcm_formula_analysis tcm_formula_analysis Read tcm_formula_weight tcm_formula_weight Read tcm_get_gene_info tcm_get_gene_info Read tcm_get_structure tcm_get_structure Read tcm_graph_embed tcm_graph_embed Read tcm_gwas_associations tcm_gwas_associations Read tcm_herb_detail tcm_herb_detail Read tcm_hypergeometric_test tcm_hypergeometric_test Read tcm_kegg_compound tcm_kegg_compound Read tcm_kegg_disease_pathways tcm_kegg_disease_pathways Read tcm_literature_mine tcm_literature_mine Read tcm_multi_enrichment tcm_multi_enrichment Read tcm_ncbi_gene_search tcm_ncbi_gene_search Read tcm_network_analysis tcm_network_analysis Read tcm_network_figure tcm_network_figure Read tcm_network_simulation tcm_network_simulation Read tcm_normalize_disease tcm_normalize_disease Read tcm_normalize_genes tcm_normalize_genes Read tcm_normalize_ids tcm_normalize_ids Read tcm_normalize_structure tcm_normalize_structure Read tcm_npass_search_compound tcm_npass_search_compound Read tcm_pubchem_lookup tcm_pubchem_lookup Read tcm_read_target_table tcm_read_target_table Read tcm_report_insight tcm_report_insight Read tcm_scrna_channel tcm_scrna_channel Read tcm_search_disease_targets tcm_search_disease_targets Read tcm_self_iterate tcm_self_iterate Read tcm_string_ppi tcm_string_ppi Read tcm_symmap_lookup tcm_symmap_lookup Read tcm_tcmbank_search tcm_tcmbank_search Read tcm_tcmsp_search tcm_tcmsp_search Read tcm_trials_match tcm_trials_match Read tcm_uniprot_idmap tcm_uniprot_idmap Read tcm_wikidata_lookup tcm_wikidata_lookup Read unified_overview unified_overview

Related servers

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

Questions about OpenTCM_Discovery

How do I prevent bulk modifications through OpenTCM_Discovery? +

The OpenTCM_Discovery server has 3 write tools including tcm_convert_dose, tcm_report_generate, tcm_smart_plan. 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 OpenTCM_Discovery.

How many tools does the OpenTCM_Discovery MCP server expose? +

69 tools across 3 categories: Execute, Read, Write. 60 are read-only. 9 can modify, create, or delete data.

How do I enforce a policy on OpenTCM_Discovery? +

Register the OpenTCM_Discovery 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 OpenTCM_Discovery tool call.

Deterministic rules across all 69 OpenTCM_Discovery tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

69 OpenTCM_Discovery tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from OpenTCM_Discovery's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.