assessment-suite
AI-assisted analytic assessment that keeps the teacher's judgement central. Two Model Context Protocol servers for Claude Desktop; the assessment logic lives in editable methodology documents.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
tikankika
Source: github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
initphase6_startphase6_methodologyphase6_rubricphase6_read_nextphase6_writephase6_statusphase6_getassessment_deleteteacher_annotationrubric_readphase6_write_freeprocess_memoassessment_purposehermeneutic_readreflect_insightsreflect_uncertaintyreflect_aspect_analysisphase2b_questionsphase4b_rubricrubric_editphase4c_savephase2c_boundariesphase2d_studentsphase3_validatejson_writeproject_repairFix path portability issues in an assessment project (RFC-015). This tool converts absolute paths (e.g., /Users/username/...) to relative paths, enabling projects to be shared across different machines. WHEN TO USE: - Project was created on a different machine/user account - MCP tools fail with "f…
project_statusGet comprehensive status of an assessment project (RFC-013: Session Continuity). WHEN TO USE: - Starting work on an existing project - Resuming after a break - Checking progress before Phase 8+ - Finding where to continue assessment WHAT IT RETURNS: - Project overview (name, created, last updated)…
phase_startphase_completeComplete a phase session and save the final document. Call this when the LLM-driven dialogue is finished and you have the final content. This tool: 1. Removes any draft section from the Complete_ report 2. Writes final phase section to Complete_ report (with markers) 3. Saves standalone file to th…
phase6_post_formatPhase 6-post: Assessment Format Detection - REQUIRED step between Phase 6 and Phase 7. Run this AFTER completing Phase 6 assessment and BEFORE Phase 7 report generation. TWO-PHASE WORKFLOW: (1) LOAD mode - Returns Q-files + sample content + methodology (2) SAVE mode - Saves detected format to exam…
student_report_updateUpdate BOTH student report files for Phase 9-12. Updates TWO files simultaneously: 1. complete_assessment/Complete_{student}.md (progressive report) 2. Phase-specific file: - Phase 9: 09_qualitative/Student_*_generalization.md - Phase 10: 10_extrapolation/Student_*_extrapolation.md - Phase…
scan_source_directoryScan directory to identify exam, rubric, and student answer files. FIRST STEP for new projects. After this returns, call initialize_project. All paths must be within the configured workspace directory. DO NOT use bash, view, ls, or Filesystem MCP - use THIS tool instead.
initialize_projectCreate project structure with folders and files. SECOND STEP - Call AFTER scan_source_directory. Then call convert_documents to process PDFs. Creates folders, copies files, generates project_state.json. Required even if markdown files already exist.
convert_documentsConvert PDF files to readable markdown text, or copy PDFs as-is. THIRD STEP - Call AFTER initialize_project. This is the ONLY way to convert PDFs. Do NOT use bash, pymupdf4llm, or Python scripts. Converts ALL PDFs in input_dir to markdown files in output_dir. Non-PDF files (.md, .txt) are copied a…
extract_student_answersExtract student answers into Q-files (one file per question). This is the ONLY way to create Q-files. Do NOT use bash, Python scripts, or manual extraction. Prefers Phase 3 annotated files from 03_material/ (marker-based extraction). Falls back to boundary matching from 02_markdown/ if no markers …
generate_reportsGenerate student reports from assessed Q-files. Modes: preview → analyze → generate (with confirmed=True). Use mode="analyze" when free-text assessments aren't parsing correctly. Input: 06_analytic_assessment/Q*.md → Output: 07_analytic_student/
quantitative_summaryGenerate quantitative JSON summaries from student reports. Call AFTER generate_reports. Creates points/percentages per student. Input: 07_analytic_student/ → Output: 08_quantitative/*.json
phase3_preparePrepare student files for Phase 3 annotation (RFC-034). Copies student markdown files from 02_markdown/student_answers/ to 03_material/student_answers/, adds <!-- student: {id} --> header and permanent line indices (0001, 0002...) to each file. Call AFTER Phase 2C/2D. Then run phase3_annotate to a…
phase3_annotateAuto-annotate student files with Phase 3 markers (RFC-034). Reads prepared files from 03_material/student_answers/, strips line indices, runs auto-annotation using answer_boundaries from exam_config.yaml, re-indexes, and writes back in-place. Call AFTER phase3_prepare. Then run phase3_validate to …
phase3_file_editEdit Phase 3 student files: insert/remove annotation markers (RFC-034). Use AFTER inspect_file to read the student file and understand its structure. Insert Phase 3 markers at exact line-index positions. Line indices (0001, 0002...) are PERMANENT — inserts/removes never change them. Workflow: insp…
inspect_fileDEBUG: Read file contents. Not for new projects - use scan_source_directory instead.
list_filesDEBUG: List directory contents. Not for new projects - use scan_source_directory instead.
METHODOLOGY_PATHTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
43/43 tools missing one or more hints — init (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); phase6_start (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); phase6_methodology (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +40 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool test coverage
22/43 tools referenced in tests (51%)
Write tests that reference each tool by name so every tool has at least one test.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/tikankika/assessment-suite)?variant=verified to the badge URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check