Robin Saige we check the tools AI agents call

meridian

io.github.ajc3xc/meridian

Persistent memory, task coordination, and HITL queue for AI coding sessions.

— the operator's own registry description reported

Publisher io.github.ajc3xc · first seen 2026-08-12 · endpoint https://usemeridian.us/mcp/sse

allow
verdict
stale-rich-solo
cluster
ok_tools
answers
175
tools served

Dependency rating derived

allow
allow — alive & usable · action ● · V n/a
allow — because answers ●, 175 tools legible (band B) ●, no confirmed drift in 2 probes ●; not yet checked: truth (3 attempts unverifiable, 0 disagreements)

Cluster stale-rich-solo · distinctiveness 0.531 (moderate). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency69 ms
vs populationtypical
protocolbehind
authopen
Can it be used? Q4 · observed
tools175
vs populationhigh
capabilities2
harnessB
Did it hold when checked? Q3–Q4 · derived
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers true0/0 agree

🔏 Signed receipt rr_2de2d98d77426f0f1ae22a72 · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Q1Does it answer?alive & usable — 2 probes ●evidence ↓
Q2What is it?action ● evidence ↓
Q3Can it be checked?V n/a for this kind ◐evidence ↓
Q4Did it hold?harness B · truth not yet run · no drift ●evidence ↓
Q5What company does it keep?stale-rich-solo · 1 on its host (context, not verdict) ◐evidence ↓

● observed · ◐ derived · ○ reported — the verdict synthesizes Q1–Q4; Q5 is context. Methodology →

History observed

Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (1 events)
datetypewhat changed
2026-08-12outcomefirst probe: ok_tools

What kind of tools these are derived

Verification only means something relative to a tool's NATURE — an email-sender has no "true answer", a generator has no answer key. Classification evidence: classified from tool names/descriptions/annotations WE OBSERVED. What checking applies to each kind (the full methodology →):

naturetoolsmeaning what checking applies
action105changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
retrieval-public49serves public factstruth-checkable against a public source — the V-ladder applies in full
generative11creates contentno answer key exists; disclosure + stability checks, never truth verdicts
computational8deterministic transformsself-checkable by re-computation and known-answer tests
orchestration2routes other toolsidentity + fronted-service disclosure checks (gateway vs costume)

Tools last seen observed

activate_profile_layer add_custom_hook add_insight add_note add_sprint_item add_sprint_item_pointer add_sprint_note add_subtask add_workspace_note add_workspace_proposal add_workspace_sprint_item advance_proposal_status analyze_model_efficiency analyze_sprint annotate_outputs answer_hitl archive_decision assign_sprint_waves batch_mutate batch_read capture_research_finding checkpoint claim_docx_region claim_file claim_sprint_item clear_capability_profile clone_profile_layer commit_proposal_promotion complete_sprint_item complete_wave_gate complete_workspace_sprint_item configure_wave_gate create_project delete_custom_hook delete_note delete_sprint_item_pointer dismiss_hitl execute_batch export_ai_log export_ai_log_artifacts fan_out_sprint_items finalize_wave_run find_outputs_by_source find_similar_equation find_similar_figure find_similar_table find_symbol_usages generate_handoff get_agent_instructions get_blog_posts get_capability_manifest get_citation_edges get_connection_log get_context_block get_custom_hooks get_document_structure get_docx_region_claims get_effective_capability_profile get_effective_profile get_file_claims get_findings get_flag_drift get_flag_registry get_goal get_graph_diff get_hitl_request get_insights get_latex_structure get_notes get_parallelizable_groups get_pinned_decisions get_planning_brief get_plugin_details get_profile_layer get_profile_layer_revisions get_project_by_name get_server_log_checkpoint get_server_logs get_session_activity get_session_brief get_session_log get_sprint_item_pointers get_sprint_items get_sprint_notes get_sprint_progress get_symbol_claims get_symbol_hotspots get_tasks get_tunnel_diagnostics get_workspace_decisions get_workspace_notes get_workspace_proposals get_workspace_settings get_workspace_sprint_items github_search idle_until_all_done idle_until_session_done index_equation index_figure index_table ingest_document ingest_document_structure insert_equation link_figure_caption link_flag_to_section link_manual_github_issue link_table_caption list_hitl_requests list_plugins list_profile_layers list_projects list_sessions load_handoff log_task merge_project merge_sprint_items paper_search pin_decision pin_workspace_decision preview_proposal_promotion promote_proposal prospect_symbol purge_ai_log read_note receive_messages reconcile_sprint_drift record_handoff_correction refresh_context refresh_tool_manifest register_session release_docx_region_claims release_file rename_project request_hitl request_manual_issue_screening_toggle reset_plugin_override reset_profile_layer resolve_citations resolve_sprint_item_pointers resume_wave run_verification save_blog_post save_finding save_profile_layer search_all search_code_semantic search_outputs search_server_logs search_synthesis search_tasks send_message set_active_repo set_agent_instructions set_capability_manifest set_capability_profile set_executor_config set_goal set_north_star set_parent_project set_sprint snapshot_graph_metrics social_search split_sprint_item start_session start_wave_run store_finding update_custom_hook update_decision update_md_section update_paragraph update_sprint_item update_workspace_settings update_workspace_sprint_item validate_assumption verify_handoff_token

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band B — usable, with rough edges.

legibility checktools passingok
name is clear & specific175/175
has a description175/175
description is substantive175/175
parameters are typed172/175172/175
parameters are described41/17541/175

175 of 175 tools graded · 175 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not yet confirmed — 3 attempt(s) currently unverifiable (rate limits, walls, or unmappable schemas — never counted against the server) · 0 disagreements.

claim classkeyverdictprimary source
tariff-duty0901.21.00unverifiableus-hts
tariff-duty6109.10.00unverifiableus-hts
tariff-duty8471.30.01unverifiableus-hts

Protocol conformance observed

2025-03-26
protocol version
session model
0.2.6
server version meridian

Capabilities: prompts tools

Drift observed

No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.

raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T19:59:21Zok_tools200692025-03-26
2026-08-12T05:34:34Zok_tools200552025-03-26

Watch or embed this verdict

verdict badge

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/io.github.ajc3xc/meridian.svg)](https://robinsaige.com/s/io.github.ajc3xc/meridian)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview