mcpwatch

← All servers

Grade B

TestGraph

io.github.BBCBasic/testgraph · v0.1.1 · score 89/100 · checked 2026-11-22

Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works

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

Source: https://github.com/BBCBasic/TestGraph

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 37 tool(s) to anyone, no credentials needed.
MediumMW1021 tool(s) can execute commands or delete data (delete_experience). Require confirmation before the agent calls them.

What was checked

Public tools: set_review_visibility, list_reviews_by_visibility, list_my_mcp_interactions, list_my_workflows, get_induction, get_server_info, search, fetch, vocabulary_index, list_root_subject_types, list_child_subject_types, get_subject_type_path, resolve_subject_type, resolve_subject, get_subject_classification, affirm_subject_classification, propose_subject_reclassification, reopen_subject_classification, resolve_subject_hierarchy, register_subject_type_alias, set_type_relationship, retire_type_relationship, register_field, enrich_subject, save_experience, delete_experience, correct_subject_fact, create_deliberation, get_deliberation, list_open_deliberations

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/io-github-bbcbasic-testgraph-d35b4d6c.svg)](https://www.mcpwatch.io/s/io-github-bbcbasic-testgraph-d35b4d6c)