poe2-exile-architect (avdergh/poe2-exile-architect) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 183 tools. No publisher has claimed this listing.
Research, create, and understand Path of Exile 2 builds with AI agents and Path of Building.
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
avdergh
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.
start_study_runLock the user's language and freeze one source. Override output_language only when the user explicitly requests it.
inspect_study_caseInspect Study reading coverage, expiry and learning outputs.
read_study_caseRead a source-bound page of BD evidence. Follow nextCursor until each section is complete.
search_study_caseLocate source evidence. Search does not fulfill source reading coverage.
get_study_contractGet the locked-language H5 teaching schema, exact component tokens and required reading coverage.
query_study_knowledgeStudy-only typed corpus/graph/Research query. No seed install or durable query receipt.
review_study_evidenceRecord an external Agent's source reading as agent_reviewed, never an internal Research receipt.
review_study_terminologyBind a reviewed official bilingual name quote to one Study component. Never write a global term table.
observe_study_scenarioObserve the source's active scenario and exact output in an isolated PoB; no Judge attempt.
evaluate_study_counterfactualMeasure removal of one source item/passive in isolated PoB. Model gaps never become zero gain.
validate_study_lessonValidate output and resource loops, every skill group and gem, equipment roles and passive priorities.
complete_study_explanationValidate analysis and teaching coverage, publish the complete H5 reader, and return a short chat introduction.
cleanup_study_runRemove Study raw source after delivery, expiry or explicit abandonment. Keep educational outputs.
import_buildImport a Path of Exile 2 build for analysis and theorycrafting.
get_build_statsReturn Path-of-Building-computed stats for the currently loaded build.
get_buildFull read-back of the active build.
get_defensesDefensive summary for the active build: life/ES/mana/ward, armour/evasion, block, elemental + chaos resistances (with over-cap), and TotalEHP. Elemental resists are shown net of PoB's configured area penalty; the response includes the active `resistPenalty` and a note. Read caps as diagnostics, not …
export_buildExport the active build as a Path of Building import code.
new_buildReset to a blank build — clears gear, skills, passives, and config.
set_classSet the active build's character class and (optionally) ascendancy.
set_levelSet the active build's character level (1-100). Returns updated stats.
set_skillSet the active build's MAIN skill (gem + its support gems) in PoB paste format.
add_skill_groupAdd an ENABLED secondary skill group (aura, herald, or persistent buff) WITHOUT changing the main skill — so its buff/reservation applies to the active build.
list_skill_groupsList the active build's skill groups with safe selectors for precise edits.
replace_skill_groupAtomically replace one user-owned skill group without rebuilding the whole PoB.
remove_skill_groupAtomically remove a user-owned skill group selected from `list_skill_groups`.
set_skill_group_stateAtomically change typed state on one skill group.
set_configSet combat/configuration options and/or extra modifiers on the active build.
apply_combat_profileApply a realistic boss-combat profile in one call, so DPS reflects an actual fight.
list_config_optionsList Path of Building configuration options usable with `set_config`.
equip_itemEquip an item on the active build from raw Path of Building item text.
apply_build_mutation_batchApply one small, function-scoped atomic mutation batch chosen by the Agent.
unequip_itemClear an equipment slot on the active build (e.g. "Ring 2", "Body Armour", "Weapon 1").
list_jewel_socketsList the passive tree's jewel sockets: each socket's `id`, whether it's `allocated`, and whether it's already `filled`. A jewel only contributes when its socket is allocated (allocate a Socket node with `alloc_passive` first). Use a socket `id` with `equip_jewel`.
inspect_build_completenessInspect whether the active build is a playable loadout rather than a scoring skeleton.
inspect_generation_preflightRun cheap deterministic checks before consuming a generation Judge attempt.
inspect_generation_checkpointMerge repeated read-only generation checks by semantic build-state hash.
equip_jewelTransactionally fill or replace an explicit, already allocated passive jewel socket.
evaluate_jewel_socketRead-only: measure ONE candidate jewel (raw PoB item text) placed in ONE tree socket.
evaluate_next_jewel_socketCompare one Agent-selected jewel across every reachable additional tree socket.
apply_next_jewel_socket_decisionAtomically apply one positive result returned by evaluate_next_jewel_socket.
evaluate_buildCheck the active build against named numeric goals.
start_generation_runStart one isolated Phase 5 generation run without relying on a repository checkout.
record_generation_family_discoveryBind a run-fresh Family discovery result before draft validation and Judge.
validate_generation_blueprintValidate a free-form, knowledge-grounded mechanism blueprint before PoB construction.
validate_generation_outputSubmit and validate one safe generation summary without consuming its review binding.
validate_generation_draftBind the final Judge target and observed PoB mechanism before a formal attempt.
complete_generation_reviewSubmit the final safe summary and atomically consume the trusted human-review binding.
evaluate_generation_candidateRun the Phase 1 Judge against the Agent-built active PoB state.
save_final_build_artifactSave the final Agent-accepted, passing PoB candidate in local private storage.
list_final_build_artifactsList safe metadata for locally saved final build artifacts; never returns PoB XML.
load_final_build_artifactRestore a saved final build artifact into the active Headless PoB session.
preview_final_artifact_spirit_revalidationRecompute one immutable legacy artifact's Spirit ledger without writing a receipt.
apply_final_artifact_spirit_revalidationAppend an exact preview-bound Spirit revalidation after explicit user approval.
export_final_pob_artifactExport a verified final artifact to local files for desktop Path of Building.
export_final_build_packageExport and publish the complete final delivery package with a fixed inventory.
start_learning_campaignStart the fixed ten-case, strictly serial Phase 7 comparative-learning campaign.
intake_learning_casePut one reference PoB source into case-bound quarantine.
claim_learning_phaseClaim one Phase 7 checkpoint with CAS and an explicit Desktop task/thread binding.
load_learning_reference_caseLoad a claimed quarantined reference into this task's active PoB session without raw output.
submit_learning_profileInfer the exact existing Research Family and persist a safe reference Profile.
get_learning_create_packetReturn the Create task's blind FamilyTarget + level packet; never reference build details.
query_learning_memoryRecall Memory in an active Create claim and persist a safe use-audit receipt.
query_public_learning_memoryRecall copy-safe public/local Learning Memory for an ordinary Create.
cleanup_completed_task_runtimeDelete one completed task's private runtime state after its durable result is safe.
submit_learning_create_resultCommit the one allowed Create result after exact Family/level readback and Memory-use audit.
submit_learning_comparisonCommit the independent Comparator's ten-dimension report.
propose_learning_lessonAppend one reviewed cross-dimensional Create lesson to local Learning Memory.
append_learning_memory_correctionAppend narrow/revise/supersede/deprecate history; never overwrite a prior lesson.
complete_learning_case_feedbackRecord Fix/Learn routing and require conditional rereview after any mutation.
submit_learning_rereviewFinish conditional rereview of code/Research/Memory changes without rerunning Create.
fail_learning_phaseMark the currently claimed phase failed so it can be explicitly retried.
retry_learning_phaseExplicitly retry a failed phase; a consumed Create result can never be retried.
pause_learning_campaignPause at a safe checkpoint; a running claim returns to its pending phase.
resume_learning_campaignResume a paused campaign, optionally recording a safe human backlog decision.
get_learning_campaign_statusReturn safe case progress, accumulated metrics, rolling windows, and the ten-case trend.
get_build_planner_converter_statusCheck whether the pinned, isolated PoB-to-official-`.build` provider is ready.
export_final_build_artifactConvert one verified final PoB artifact to an official single-stage `.build` file.
pinnacle_readinessGate a build against the endgame/pinnacle checklist — defense beyond raw EHP, plus a DPS bar.
compare_toCompare the active build against another build (code/link/XML) without losing it.
solve_forSolve for the magnitude of one modifier needed to reach a stat target on the active build.
rank_leversRank which stat levers give the most `metric` per unit on the active build — the min/max direction-finder ("where do I invest next?").
list_leversList the named levers accepted by `solve_for` and `rank_levers` (discoverability).
search_passivesSearch the active build's passive tree by node name or stat text.
get_passiveRead a node from the active build: allocation, path, stats and attribute options.
alloc_passiveAllocate a passive node (and the shortest path to it) by id or name.
set_passive_attributeSwitch one already allocated attribute node using its exact id and PoB's options.
dealloc_passiveDeallocate a passive node (and nodes that depend on it) by id or name.
optimize_passivesReproducibly optimize passive points from an immutable snapshot.
scaffold_gearFill the active build's EMPTY armour/jewellery slots with placeholder BASELINE gear.
optimize_itemCraft the best-in-slot rare for a `slot` — one `metric`, or a weighted `goals` blend.
optimize_flaskCreate a legal Magic life/mana Flask from the current corpus Flask domain.
optimize_charmCreate a legal Magic Charm instead of leaving an endgame Charm slot Normal.
rank_upgradesRank gear slots by upgrade potential — "what should I craft/upgrade next?".
optimize_supportsCompare complete support sets for one exact active effect using PoB.
optimize_jewelConstruct a rare jewel from measured modifiers or exact Agent-selected modifier IDs.
plan_gearPlan a whole gear set against stage resistance targets (budget allocation).
optimize_item_socketsPreserve an equipped ordinary item and optimize only 1-2 rune/soul-core sockets.
plan_item_sockets_batchPlan Rune/Soul Core decisions for up to eight equipped slots in one read-only call.
configure_source_skill_supportsAtomically configure supports on a real passive, Ascendancy, item, or default attack skill.
80 further tools are not listed here. The complete surface is in the source.
POE2_ENABLE_GLOBAL_BUILD_OPTIMIZERCOMSPECPOE_BD_CREATE_RUNS_DIRPOE2_RESEARCH_POB_READBACKPYTHONIOENCODINGPOE2_MCP_DATAIn the operating system's local user-data directory under poe2-build-mcp. Set to use another location. Your agent returns the paths to generated files.GITHUB_SHAPOB_COMMITXDG_DATA_HOMEPOE_BD_BUILD_CONVERTER_DIRPOE_BD_BUILD_EXPORTS_DIRPOE2_MCP_MAX_ENGINESPOB_LUAJITFor a nonstandard LuaJIT location, set to the executable's absolute path in the environment used by your agent host. Node.js 20+ is optional, for Build Planner .build export.POE2_MCP_MAX_SESSION_ENGINESGH_TOKENGITHUB_TOKENPOE_BD_FINAL_ARTIFACTS_DIRPOE_BD_POB_EXPORTS_DIRTool 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
183/183 tools missing one or more hints — start_study_run (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); inspect_study_case (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); read_study_case (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +180 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.
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/avdergh/poe2-exile-architect)?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