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

Meridian

175 tools. 96 can modify or destroy data without limits.

15 destructive tools with no built-in limits. Policy required.

Last updated:

96 can modify or destroy data
79 read-only
175 tools total

Community server · catalogue entry checked 10/08/2026 · full schemas captured for 171 of 175 tools

How to control Meridian ↓

What Meridian exposes to your agents

Read (79) Write / Execute (81) Destructive / Financial (15)

What Meridian costs in tokens

67,711 tokens of tool definitions, loaded on every request
34% of a 200k context window
2,636 heaviest tool: generate_handoff
Critical Risk

The most dangerous Meridian tools

96 of Meridian's 175 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Meridian

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

Deny destructive operations
{
  "archive_decision": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

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

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "analyze_model_efficiency": {
    "limits": [
      {
        "counter": "analyze_model_efficiency_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 Meridian — 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 MERIDIAN →

Instant setup, no code required.

All 175 Meridian tools

DESTRUCTIVE 15 tools
Destructive archive_decision [SUPPORT] Archive a pinned decision by id. Soft-deletes to preserve the audit trail. Use when something was fi Destructive batch_mutate [SUPPORT] 133bfff6 — run a batch of TRANSACTIONAL mutation entries in ONE call, mixing entry kinds selected pe Destructive claim_sprint_item Claim a pending sprint item: sets status to in_progress and records claimed_at + actor. Read-only: false. Reje Destructive clear_capability_profile [SUPPORT] 02038afe — Delete a scope's ENTIRE capability profile row (both its capabilities and its disabled_ca Destructive clone_profile_layer [SUPPORT] 0bec79a7 (PROFILE-5) — Copy one layer's fields/reset_fields/provenance onto another scope, going thr Destructive delete_custom_hook [MAINTENANCE] 273287cb — delete a user-defined hook by id (the id returned by add_custom_hook / get_custom_hoo Destructive delete_note [MAINTENANCE] Hard-delete a project note by id. Persistent-state disclosure: on hosted Meridian, supplied text Destructive delete_sprint_item_pointer [MAINTENANCE] 2976e168 — delete ONE generic pointer from a sprint item by its pointer id (the id returned by a Destructive fan_out_sprint_items [SUPPORT] Bulk-insert sprint items from a single orchestrator call — decompose a goal into parallel work items Destructive purge_ai_log [MAINTENANCE] c0168425 — Project-scoped, cutoff-based retention sweep spanning BOTH ai_log_events (meridian.db Destructive record_handoff_correction [MAINTENANCE] 3af86d28 — record a corrective handoff when a blocked executor session reaches a wall after rece Destructive release_docx_region_claims [MAINTENANCE] f7ee1ba7 — Release scoped docx-region claims held by a session. Without element_id releases all Destructive request_hitl Surface a question to the human-in-the-loop queue. ALWAYS use this to ask the human a question — never just as Destructive reset_plugin_override [MAINTENANCE] Clear a tenant's stored command/config override for one plugin slot, resetting it back to the bu Destructive reset_profile_layer [SUPPORT] 0bec79a7 (PROFILE-5) — Delete a scope's ENTIRE profile-layer row so it reverts to purely inheriting
WRITE 76 tools
Write activate_profile_layer [SUPPORT] 0bec79a7 (PROFILE-5) — Advance a hosted_default layer's lifecycle to 'active' — the single 'publish' Write add_custom_hook [MAINTENANCE] 273287cb — define a user-creatable Claude Code hook (PreToolUse | PostToolUse | Stop), generaliz Write add_insight [SUPPORT] Record a durable STRATEGIC INSIGHT — accumulated understanding that generates future decisions. A fi Write add_note [SUPPORT] Add a per-project wiki note (setup, gotcha, howto, env, ...). Free-form title/body; comma-separated Write add_sprint_item ALWAYS call get_sprint_items first to check for existing pending items before adding. Append a todo item to th Write add_sprint_item_pointer [SUPPORT] 2976e168 — attach a GENERIC POINTER to a sprint item: a portable, composable reference to a thing-in Write add_sprint_note [SUPPORT] Add an ephemeral note to the current session's scratch pad. Use for constraints, blockers, working a Write add_subtask [SUPPORT] Add a child sprint item under an existing parent item. Inherits the parent's version. Status starts Write add_workspace_note [MAINTENANCE] Add a workspace-level wiki note that applies across ALL projects in this workspace (onboarding, Write add_workspace_proposal Capture a workspace-level flash of insight into the 'drawer of inspiration' — cross-project ideas that don't b Write add_workspace_sprint_item [MAINTENANCE] Add an item to the workspace-level personal backlog — a cross-project board NOT tied to any sing Write advance_proposal_status [SUPPORT] Transition a workspace proposal through its lifecycle. Enforced transitions: raw → investigating|rej Write annotate_outputs [SUPPORT] 9e02e448 — capture a human annotation for a path inside an outputs tree WITHOUT touching the filesys Write answer_hitl [SUPPORT] Answer a pending HITL request programmatically. Marks it answered so the waiting session can resume. Write assign_sprint_waves [MAINTENANCE] 58a45b92 — PERSIST the parallel grouping: writes the conflict-free batches get_parallelizable_gr Write capture_research_finding [SUPPORT] Inline capture for web/paper research during planning: save a finding from a URL as an addressable n Write checkpoint [SUPPORT] Save progress mid-session. Runs auto_capture (buckets done tasks into a note), generates a delta han Write claim_docx_region [MAINTENANCE] f7ee1ba7 — Model B scoped-region claiming for .docx files. Claim a specific paragraph/element by Write claim_file [SUPPORT] Claim edit rights on a file for this session. Whole-file by default (auto-expires after 2 hours). Fo Write commit_proposal_promotion [SUPPORT] Commit a proposal's promotion through 'depth' (ce4883f3), cumulative over every shallower depth. Req Write complete_sprint_item Mark a sprint item done. Pass task_id to link the task that shipped it. Pass session_id to get a board_change Write complete_workspace_sprint_item [MAINTENANCE] Mark a workspace personal-backlog item done (stamps completed_at). Returns the updated item. Per Write configure_wave_gate [SUPPORT] 74a8f420 — PLANNING: configure (or on-the-fly reconfigure) a deterministic action pipeline attached Write create_project [MAINTENANCE] Create a new Meridian project. Persistent-state disclosure: on hosted Meridian, supplied text an Write dismiss_hitl [SUPPORT] Dismiss a HITL request (won't-answer / no longer relevant). Stays in audit trail. Use list_hitl_requ Write export_ai_log [MAINTENANCE] c0168425 — Read-only: project-scoped, receipted export of ai_log_events (meridian.db.ai_log — th Write export_ai_log_artifacts [MAINTENANCE] c0168425 — Read-only: project-scoped, receipted export of stored ai_log artifacts (meridian.arti Write finalize_wave_run [SUPPORT] 2a654cb0 — IDEMPOTENT FINALIZATION: close a wave run opened by start_wave_run. Safe to retry: if the Write generate_handoff EXECUTOR SESSIONS: MANDATORY - call at end of every session before disconnect. Never write markdown manually. Write index_equation [MAINTENANCE] 06df6ab3 — index ONE Word equation (OMML) against a document already stored in the doc-structure Write index_figure [MAINTENANCE] c623e648 — index ONE figure into the SEMANTIC figure index against a document already stored in Write index_table [MAINTENANCE] 2622182d — index ONE table into the SEMANTIC table index against a document already stored in th Write ingest_document [SUPPORT] Turn a Word/PDF/text document into a queryable kind='document' note with a source link — a report, t Write ingest_document_structure [MAINTENANCE] db42acce — persist pre-parsed structural data (headings/figures/tables) into the doc-structure s Write insert_equation [MAINTENANCE] 51a595e7 — write an OMML equation DIRECTLY into a stored document's source .docx (real OOXML wri Write link_figure_caption [MAINTENANCE] 0ff8b982 — DURABLY link an already-indexed figure (doc_figures row) to its caption paragraph (a Write link_flag_to_section [MAINTENANCE] 8ca89e8f — DURABLY link a docx section/paragraph/figure/table (any doc_elements id — the same id Write link_manual_github_issue [SUPPORT] 5dfe34b2 — attempt to link a manually-filed GitHub issue (one Meridian did NOT create) to a sprint i Write link_table_caption [MAINTENANCE] 42d398a5 — DURABLY link an already-indexed table (doc_tables row) to its caption paragraph (a do Write log_task [SUPPORT] Log a task this session completed or is working on. Valid statuses: pending, in_progress, done, fail Write merge_project [MAINTENANCE] d6bd60e0 — merge a phantom-duplicate project INTO another. Re-parents EVERY child row of the sou Write merge_sprint_items [SUPPORT] Merge multiple sprint items into one. Source items are closed (skipped, merged_into=survivor). Retur Write pin_decision [SUPPORT] Create a pinned decision (editable constitution row). Use for the current authoritative truth that s Write pin_workspace_decision [MAINTENANCE] Pin a workspace-level decision that applies across ALL projects (shared architecture, org-wide s Write promote_proposal Promote a workspace proposal into a real sprint item, creating the link between them. The proposal must be in Write register_session [MAINTENANCE] Low-level: register this session without loading goal context. Use start_session instead for exe Write release_file [SUPPORT] Release a file lock (and any symbol claims this session holds on it). Persistent-state disclosure: o Write rename_project [MAINTENANCE] 7acb8563 — rename a project. Returns the updated project, or {error} if it does not exist. Persi Write request_manual_issue_screening_toggle [SUPPORT] 5dfe34b2 — request enabling/disabling the OFF-by-default opt-in extension that lets the automated Gi Write resolve_citations [MAINTENANCE] fefb596a — resolve this project's in-text citation markers to canonical Zotero items via Zotero' Write resolve_sprint_item_pointers [SUPPORT] 2976e168 — resolve EVERY generic pointer on a sprint item to its concrete location, dispatching by s Write save_blog_post [MAINTENANCE] Create or update a workspace-scoped blog post (draft|published|archived lifecycle). Posts belong Write save_finding [SUPPORT] Phase-agnostic capture primitive: turn a finding into a durable, addressable note with provenance — Write save_profile_layer [SUPPORT] 0bec79a7 (PROFILE-5) — Validate and persist ONE layer of the hosted_default -> workspace -> user -> Write send_message [MAINTENANCE] PARALLEL COORDINATION (d3a3a01d): enqueue an actor-model message to another session (session_mes Write set_active_repo [MAINTENANCE] Update the tunnel's active Serena repo at runtime. When a planning session switches to a differe Write set_agent_instructions [MAINTENANCE] Set or update the custom agent_instructions for a project. Instructions are injected into every Write set_capability_manifest [SUPPORT] 649e095f — Persist a project's structured capability manifest: a list of capability declarations, ea Write set_capability_profile [SUPPORT] 02038afe — Persist ONE layer of the capability-inheritance chain: workspace -> user -> project -> sp Write set_executor_config [MAINTENANCE] Store per-project executor defaults (repo_path, env_file, test_cmd, test_min, deploy_cmd, shell_ Write set_goal [MAINTENANCE] Set or update the goal state. Persistent-state disclosure: on hosted Meridian, supplied text and Write set_north_star [MAINTENANCE] Update only the north star — the long-lived product vision that rarely changes. Distinct from th Write set_parent_project [MAINTENANCE] 7acb8563 — set, change, or clear a project's parent AFTER creation (create_project only accepted Write set_sprint [MAINTENANCE] Update only the sprint — the short-term focus that changes each session or week. Any team member Write snapshot_graph_metrics [MAINTENANCE] Record a code-graph snapshot for a session (node count, edge count, hotspot count, file churn). Write split_sprint_item [SUPPORT] Split a sprint item into multiple smaller items. The original is closed (skipped) and N new items ar Write start_wave_run [SUPPORT] 2a654cb0 — DURABLE WAVE STATE: open a wave run before dispatching a parallel wave. Returns an immuta Write store_finding [MAINTENANCE] PARALLEL COORDINATION (c35370cc): persist a per-task intermediate result to the session_findings Write update_custom_hook [MAINTENANCE] b4f4627f — the previously-missing generic enable/disable/edit path for a user-defined hook (id r Write update_decision [SUPPORT] Patch a pinned decision. Pass new_title + new_body to atomically supersede (creates a new active row Write update_md_section [MAINTENANCE] Propose a replacement for an anchored section of an agent template doc (CLAUDE.md or AGENTS.md). Write update_paragraph [MAINTENANCE] f978e588 — ID-addressable docx WRITE (the write counterpart of the get_element_by_id / paraId re Write update_sprint_item [SUPPORT] Edit fields on an existing sprint item: title, version, notes, human_id (assignee), group, deferred_ Write update_workspace_settings [MAINTENANCE] Update workspace-global default settings. Pass only the fields you want to change. hitl_auto_ans Write update_workspace_sprint_item [MAINTENANCE] Edit a workspace personal-backlog item: title, status, group, or human_id (assignee). Only the f Write validate_assumption [SUPPORT] Confirm or invalidate the assumption a pinned decision rests on, in one call — no phase switching. S
READ 79 tools
Read analyze_model_efficiency [MAINTENANCE] 0fba4cb6 — MECHANICAL (zero-token) model-tier suggestion for a task or sprint item. Deterministi Read analyze_sprint [MAINTENANCE] PLANNING: Read-only synthesis of the current sprint into one structured brief — parallelizabilit Read batch_read [SUPPORT] 133bfff6 — run a batch of DOMAIN-AWARE, CONCURRENT read requests in ONE call. Each request names an Read find_outputs_by_source [SUPPORT] 2ae25966 — READ-ONLY reverse provenance lookup over a run's OUTPUTS tree: the mirror image of resolv Read find_similar_equation [MAINTENANCE] 06df6ab3 — fuzzy-match a LaTeX string against every equation already indexed (via index_equation Read find_similar_figure [MAINTENANCE] c623e648 — fuzzy-match a free-text description OR a file path against every figure already index Read find_similar_table [MAINTENANCE] 2622182d — fuzzy-match a free-text description against every table already indexed (index_table) Read find_symbol_usages [MAINTENANCE] 9605edb0 — READ-ONLY cross-reference tracking: given a document and EITHER a doc_equations row i Read get_agent_instructions [MAINTENANCE] Read-only: Return the custom agent_instructions for a project. These are injected automatically Read get_blog_posts [MAINTENANCE] Read-only: List workspace-scoped blog posts, newest first. Optional 'status' filter (draft|publi Read get_capability_manifest [SUPPORT] 649e095f — Read-only: return a project's structured capability manifest (id/purpose/required_tools/f Read get_citation_edges [MAINTENANCE] fefb596a — read the CITATION GRAPH of a project's ingested documents. Returns every in-text cita Read get_connection_log [MAINTENANCE] Read-only: Return the recent /mcp connection-event log for this tenant (newest first, up to 200 Read get_context_block [SUPPORT] Read-only: Return a compact project context block (north star, sprint, pending sprint items, recent Read get_custom_hooks [MAINTENANCE] 273287cb — list a project's user-defined hooks (newest first). Optional event filter and enabled Read get_document_structure [SUPPORT] 13462df2 — return the heading outline of a Word .docx WITHOUT ingesting it as a note. Meridian parse Read get_docx_region_claims [MAINTENANCE] f7ee1ba7 — Read-only: list active scoped docx-region claims on a file (who owns which element_id Read get_effective_capability_profile [SUPPORT] 02038afe — Read-only: resolve and return the MERGED capability profile for a project (optionally nar Read get_effective_profile [SUPPORT] 0bec79a7 (PROFILE-5) — Read-only: resolve and return the MERGED profile for a project across every a Read get_file_claims [SUPPORT] Read-only: show active claims on a file — the whole-file lock (with the holder's session name, if an Read get_findings [MAINTENANCE] Read-only (c35370cc): read stored session_findings for a project (newest first), optionally scop Read get_flag_drift [MAINTENANCE] 8ca89e8f — read side of link_flag_to_section: for every recorded flag link (optionally scoped to Read get_flag_registry [SUPPORT] 45802b67 — scan a source tree for os.environ.get(...) / os.getenv(...) call sites (AST-based, not re Read get_goal [SUPPORT] Read-only: Fine-grained — return just the goal fields (north_star, sprint, version_goal) in isolatio Read get_graph_diff [MAINTENANCE] Read-only: compare the latest code-graph snapshots of two sessions — returns delta in node_count Read get_hitl_request [SUPPORT] Read-only: Poll a HITL request for the human's answer. Returns the row including status ('pending'|' Read get_insights [SUPPORT] Read-only: List a project's strategic insights (newest first), optionally filtered by horizon (perma Read get_latex_structure [SUPPORT] 106118cd — parse a LaTeX (.tex) source's structure WITHOUT a PDF intermediary. Meridian parses the . Read get_notes [SUPPORT] Read-only: List project notes (newest first), LIGHTWEIGHT by default — each item is id/slug/title/ta Read get_parallelizable_groups [MAINTENANCE] Read-only: Return clusters of pending sprint items that are safe to run simultaneously. Filters Read get_pinned_decisions [SUPPORT] Read-only: List pinned decisions, highest priority first (urgent → normal → low, then newest-first). Read get_planning_brief PLANNING SESSIONS: CALL THIS FIRST before anything else. Read-only: Return a compact planning context — sprint Read get_plugin_details [MAINTENANCE] Read-only: Full schema for one named plugin (all tool definitions, description overrides, and st Read get_profile_layer [SUPPORT] 0bec79a7 (PROFILE-5) — Read-only: return the raw, single-layer profile for one (scope_type, scope_id Read get_profile_layer_revisions [SUPPORT] 0bec79a7 (PROFILE-5) — Read-only: the hosted_default revision/audit history for one scope_id, newest Read get_project_by_name [MAINTENANCE] Read-only: Find a project by name — look up, search, or resolve a project's project_id from its Read get_server_log_checkpoint [MAINTENANCE] b241a437 -- Read-only: Return the positional/checkpoint index for the server_logs ring-buffer. T Read get_server_logs [MAINTENANCE] Read-only: Return recent application-level WARNING/ERROR/EXCEPTION log records (newest first, up Read get_session_activity [MAINTENANCE] Read-only: Return the raw MCP-tool-call heartbeat feed for the given executor session — a ring-b Read get_session_brief [SUPPORT] Read-only: Call this FIRST for project summaries or to see what a session did — returns session, tas Read get_session_log [MAINTENANCE] Read-only: Return the full task log for the given session. Returns every log_task description lo Read get_sprint_item_pointers [SUPPORT] 2976e168 — list the GENERIC POINTERS attached to a sprint item (oldest first). Each pointer is {id, Read get_sprint_items Read-only: List sprint items for a project. Optional status filter (todo|pending|in_progress|provisional_compl Read get_sprint_notes [SUPPORT] Read-only: Get all ephemeral scratch-pad notes for the current session. Shown at the top of session Read get_sprint_progress [SUPPORT] Read-only: Return a SUMMARY of sprint items by status (pending/in_progress/done/failed) optionally f Read get_symbol_claims [MAINTENANCE] Read-only: list symbol-level claims on a file (who owns which class/function/method line ranges) Read get_symbol_hotspots [MAINTENANCE] Read-only: symbols claimed by 3+ distinct sessions within 14 days — a refactor/ownership smell. Read get_tasks [SUPPORT] Read-only: Get recent tasks across all sessions. Read get_tunnel_diagnostics [MAINTENANCE] f1e0df55 — Read-only: ONE layered diagnostic snapshot of your tunnel/connectors, separating what Read get_workspace_decisions [MAINTENANCE] Read-only: List workspace-level pinned decisions (active only by default, newest first). Read get_workspace_notes [MAINTENANCE] Read-only: List workspace-level notes (newest first). Optional ?tag substring filter. Read get_workspace_proposals [SUPPORT] Read-only: List a bounded page of workspace proposals (human-authored flashes of insight), newest fi Read get_workspace_settings [MAINTENANCE] Read-only: Read workspace-global default settings (applies across ALL projects in this workspace Read get_workspace_sprint_items [MAINTENANCE] Read-only: List workspace personal-backlog items (grouped by 'group', then position). Optional ' Read github_search [SUPPORT] Search GitHub — a REAL external lookup (keyless), sibling to paper_search/social_search for external Read idle_until_all_done [MAINTENANCE] PARALLEL COORDINATION (d3a3a01d): non-blocking barrier check across sibling sessions. Returns {a Read idle_until_session_done [MAINTENANCE] Read-only: Poll every 30 seconds until another session is closed or archived. Use this when you Read list_hitl_requests [SUPPORT] Read-only: List HITL requests without needing UUIDs. OMIT project_id to list pending HITLs across AL Read list_plugins [MAINTENANCE] Read-only: Lightweight index of active tunnel plugins — name, description, enabled state, and to Read list_profile_layers [SUPPORT] 0bec79a7 (PROFILE-5) — Read-only: enumerate every persisted profile_layers row across the 5-layer ho Read list_projects [MAINTENANCE] Read-only: List all projects — find, browse, or look up your projects and their IDs. Call this f Read list_sessions [MAINTENANCE] Read-only: List active sessions for a project. Useful for planning chat to see what's currently Read load_handoff [MAINTENANCE] Read-only: Return the latest stored handoff for a project as an MCP tool result — a trusted-chan Read paper_search [SUPPORT] Search academic papers — a REAL external lookup (keyless). Per the research-routing protocol, use th Read preview_proposal_promotion [SUPPORT] Read-only (ce4883f3): preview what commit_proposal_promotion would do for a proposal at a given dept Read read_note [SUPPORT] Read-only: Fetch one project note's full body by its per-project slug (the slug field from get_notes Read receive_messages [MAINTENANCE] PARALLEL COORDINATION (d3a3a01d): fetch unread messages addressed to a session (oldest first) an Read reconcile_sprint_drift [MAINTENANCE] Read-only: Cross-reference pending sprint items against recent git commits and return items that Read refresh_context [SUPPORT] Single-call post-compaction recovery for planning chats. Returns a COMPACT snapshot — current sprint Read refresh_tool_manifest [MAINTENANCE] Read-only: return the authoritative, compact manifest of ALL built-in Meridian MCP tools (name + Read resume_wave [SUPPORT] efaa918a — STALE-MANIFEST GATING: check whether a wave run opened by start_wave_run is still safe to Read search_all [SUPPORT] Read-only: Universal search across all project content: tasks, notes, pinned decisions, and sprint i Read search_code_semantic [SUPPORT] 93fce816 — Cursor-style LOCAL semantic code search over a source tree, entirely in a DuckDB sidecar Read search_outputs [SUPPORT] a0e9133e — READ-ONLY full-text search over a run's OUTPUTS tree (numeric/tabular/array artifacts), b Read search_server_logs [MAINTENANCE] 222d54f8 — BM25 full-text search over the server_logs ring-buffer. Complements get_server_logs ( Read search_synthesis [SUPPORT] Read-only: Natural-language search that returns a short, CITED answer (which notes/items it drew fro Read search_tasks [SUPPORT] Read-only: Search tasks by keyword or natural-language query. Uses trigram similarity on Postgres, L Read social_search [SUPPORT] Search public social-media / discussion content — a REAL external lookup (keyless), sibling to paper Read verify_handoff_token [MAINTENANCE] Read-only: Verify a handoff provenance token (dd07ece0). When a /goal block is copy-pasted into

Related servers

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

Questions about Meridian

Can an AI agent delete data through the Meridian MCP server? +

Yes. The Meridian server exposes 15 destructive tools including archive_decision, batch_mutate, claim_sprint_item. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Meridian? +

The Meridian server has 76 write tools including activate_profile_layer, add_custom_hook, add_insight. 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 Meridian.

How many tools does the Meridian MCP server expose? +

175 tools across 5 categories: Destructive, Execute, Financial, Read, Write. 79 are read-only. 96 can modify, create, or delete data.

How do I enforce a policy on Meridian? +

Register the Meridian 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 Meridian tool call.

Deterministic rules across all 175 Meridian tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

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

// WHERE THIS COMES FROM

These policies come from Meridian'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.