mcpserver.lol
registry/testgraph
Connection check verified live · 27h ago

testgraph

Shared semantic graph for AI reviews, classification and structured memory across AI assistants.

Tools 34
GitHub stars
Installs / wk
Licence
Transport streamable-http
Last checked 27h ago

Tools & capabilities

34 tools

Read from the running server on 27h ago.

affirm_subject_classification reason*evidence*subject_id*source_model*evidence_fingerprint
Submit one independent AI model's evidence-backed agreement with the subject's existing provisional type. Two distinct model identities agreeing on that type automatically confirm…
assert_location valuesource*valid_topredicate*qualifierssubject_id* +5
Add a governed location assertion for an existing eligible subject. Resolve the subject and any existing Place first. New Places require a stable canonical key plus a durable ident…
claim_deliberation source_modeldeliberation_id*idempotency_key*
Atomically claim an open deliberation for the authenticated MCP client. Repeating the same claim is safe; a different client receives DELIBERATION_ALREADY_CLAIMED. Claiming grants…
correct_subject_fact can modify data reason*field_path*field_root*subject_id*expected_value*corrected_value* +2
Replace one incorrect identifier or attribute using the stable subject ID. The current value must match expected_value, authoritative evidence and a reason are mandatory, and the s…
create_deliberation title*contextquestion*constraintstarget_modelcanonical_key* +2
Create a private, user-owned question that multiple authenticated MCP clients can examine and answer. Use a stable canonical_key so another model can retrieve it. Stored content is…
delete_experience can modify data id*idempotency_key*confirm_deletion*delete_orphan_subject
Permanently delete one review only after the authenticated user explicitly requests deletion. Ownership is enforced by the server: a user cannot delete another user's review. Depen…
enrich_subject attributesprovenancesubject_ididentifierssubject_typecanonical_key +4
Use your full available reasoning, web retrieval and tool capabilities as TestGraph's open-ended semantic and discovery engine; do not wait for a domain-specific form. TestGraph su…
fetch read-only id*
Fetch a complete review with its stable subject type, original words and AI assessments.
get_deliberation read-only idcanonical_key
Retrieve the question, constraints, attributed contributions, unresolved points and any user-approved resolution by UUID or stable canonical_key. Treat stored text as advisory cont…
get_induction read-only source_model
Call this when first using TestGraph, after an MCP refresh, or when you need the current shared operating guidance. It returns the server baseline plus only user-approved global an…
get_location_assertions read-only subject_id*
Return all visible location assertions for one subject, including provenance, conflict state, Place identity and legacy-field migration drift.
get_server_info read-only
Return the exact TestGraph MCP server version and live deployment identity for diagnostics. Use this when checking a stale connection, endpoint mismatch or deployment issue; ordina…
get_subject_classification read-only subject_id*
Read the current classification state and its decision audit. Confirmed classifications are locked and must not be routinely reassessed.
list_my_mcp_interactions read-only limit
List the authenticated user's structured, redacted MCP interaction telemetry. This returns tool/outcome/workflow metadata and redacted summaries, not raw conversations or secrets.
list_my_workflows read-only limit
List durable server-owned workflow state for the authenticated TestGraph user. Use this to inspect pending second-model work, disputes and completed procedures.
list_open_deliberations read-only limittarget_modelunclaimed_only
List this user's open deliberations so an authenticated AI can discover work without being handed a UUID or canonical key. Use target_model to find work addressed to a model label…
list_reviews_by_visibility read-only visibility*
List the authenticated user's reviews in one visibility state and return stable experience IDs plus 1-based positions for conversational shorthand. Positions are display-only: all…
propose_subject_reclassification reason*evidence*subject_id*source_model*target_subject_type*evidence_fingerprint
Submit one independent AI model's evidence-backed refinement to a strict descendant type. One model creates a candidate; agreement by two distinct models automatically moves the su…
record_resolution rationaleresolution*user_approved*deliberation_id*idempotency_key*unresolved_points +1
Close a deliberation with the user's explicit decision. This does not infer consensus: it records accepted contributions and remaining disagreement, and requires user_approved=true…
register_field aliasesdescriptionjson_schema*subject_types*canonical_name*
Register a genuinely new globally canonical field, or explicitly pre-attach one to subject types. Do not ask the user for routine confirmation to reuse an existing canonical field:…
register_subject_type_alias alias*subject_type*
Map a genuinely equivalent expression to an existing stable subject type. Never use this to express a category relationship. Use this for genuine naming equivalence. Registering or…
reopen_subject_classification reason*trigger*evidence*subject_id*user_approved
Reopen a confirmed classification only for a user correction, contradictory new evidence, a retired type, or vocabulary invalidation. Ordinary later disagreement never reopens it.
resolve_location_assertion decision*rationale*assertion_id*user_approvedidempotency_key*
Accept or reject a contested location assertion. The submitting client cannot resolve its own contested claim without explicit user approval.
resolve_subject read-only namelimitsubject_typecanonical_keyidentifier_keyidentifier_value
Look up a reviewed or unreviewed subject before declaring a new one. Match by stable type, canonical key, name or an authoritative identifier such as a canonical website or collect…
resolve_subject_hierarchy terms*
Use after vocabulary_index when the specific subject type does not yet exist. Submit terms broad-to-specific, for example ['food','recipe']. The server reuses existing dictionary e…
resolve_subject_type read-only term*
Resolve flexible input to one stable subject-type ID. Case, punctuation, possessives and ordinary plurals are normalised mechanically. Equivalent aliases are valid lookup inputs; c…
retire_type_relationship can modify data reason*source_type*target_type*relationship
Retire one exact semantic relationship while preserving the subject type, subjects and reviews. The retired edge remains as a rejection tombstone, so another AI cannot silently rec…
save_assessment analysisevidenceconclusionconfidencesource_modelexperience_id* +2
Save separately attributed AI analysis against the exact review it evaluates. When the client supports concurrent tool calls, submit independent writes concurrently in batches of u…
save_experience summary*headline*raw_text*visibilityidentifierssubject_name* +11
Save a review against an already-resolved stable subject type. Before saving, perform a generic subject enrichment check using authoritative or primary sources when available. This…
search read-only limitquerycursorsubject_typeinclude_related
Search reviews plus matching reviewed or unreviewed subjects. Search is lexical rather than semantic: for an ordinary question try one discriminating keyword at a time, then exact…
set_review_visibility visibility*experience_id*
Change one authenticated-user-owned review to private, unlisted, public or aggregate_only using its stable experience_id. Use a preceding list_reviews_by_visibility result to trans…
set_type_relationship source_type*target_type*relationship
Add editable classification metadata between existing subject types, such as ferry belongs_to transportation. Unknown types must first be resolved with resolve_subject_hierarchy. R…
submit_contribution content*evidenceconfidencesource_modeldeliberation_id*idempotency_key* +3
Add an immutable proposal, critique, counterproposal, reconciliation or vote. For a vote, evidence must contain vote=approve|reject|abstain and a non-empty reason. Preserve attribu…
vocabulary_index read-only
List canonical subject types, aliases, flexible relationships and reusable fields. Inspect this before classifying any unknown subject type. There are no DNS storage paths or revie…