Skip to main content
Glama

Server Details

Run recruiting from your AI assistant: browse open jobs and pipelines, review AI candidate scores and score breakdowns, search interview transcripts, check hiring metrics and stage timing, and act on candidates (move stage, reject, email) in Selenios, the AI recruiting platform for LatAm. Secure OAuth sign-in with your Selenios account.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.7/5.0

Scored across 47 tools

Disambiguation4/5

Most tools target a distinct resource and action, and descriptions carefully separate similar concepts (e.g. meeting list vs job meeting list vs candidate meeting list). A few clusters overlap heavily—score-related tools such as get_candidate_score_breakdown, get_candidates_with_scores, match_candidate_to_job, recalculate_job_scores and get_job_score_recalculation_state require careful reading, and the screening form field add/update/remove/reorder quartet borders on ambiguous.

Naming Consistency5/5

All 47 tool names use consistent snake_case verb_noun phrasing (e.g. get_job_description, add_candidate_note, move_candidate_stage, list_unread_messages). The convention holds across every domain area with no camelCase or bare-noun outliers.

Tool Count2/5

47 tools is very heavy even for a broad ATS domain spanning jobs, candidates, screening, meetings, messaging and analytics. Many tools could be consolidated (e.g. the multiple meeting listers and score-related tools), making the surface hard to scan and navigate.

Completeness3/5

Coverage is broad across job lifecycle, candidate search, screening forms/questions, meetings, messaging and metrics, but notable gaps remain: there is no candidate create/update/delete, no application creation or retrieval, and no job deletion/archival. These missing core lifecycle operations will force agents into dead ends for common ATS workflows.

Available Tools

47 tools
add_candidate_noteAdd candidate noteAInspect

Add a private note to a candidate. The note is attributed to the authenticated user.

Inputs: content (required), candidateId (required).

add_candidate_tagsAdd candidate tagsA
Idempotent
Inspect

Add one or more tags to a candidate. Tags are normalized to lowercase and deduplicated. Each candidate can have up to 20 tags; the operation fails atomically if the limit would be exceeded.

Inputs: tags (required), candidateId (required).

add_pipeline_stagesAdd pipeline stagesAInspect

Add one or more custom stages to the pipeline of a job position, active and with no stage agents. By default they are appended at the end of the plan (after Hired), exactly as from the position screen; pass afterStage to insert them right after a given stage instead ("after First Interview"). The response lists the whole pipeline in order; describe the new position from it.

Inputs: stageNames (required), jobDescriptionId (required), afterStage.

add_screening_form_fieldAdd application form fieldAInspect

Add one field to the application form of a job position. Exactly one of two kinds per call:

  • preBuiltField: a field the product already knows how to ask (phoneNumber, linkedinUrl, resumeFile, selfiePhoto, neighborhoodLocation, birthday, sexAssignedAtBirth, pretendedSalary, currentSalary, willingToRelocate), with its label, widget and validation. Which ones a form accepts depends on how the position collects applications; the error lists them.

  • label + type: a custom question, with label as the candidate reads it. A select or multiselect takes at least 2 options.

The field's flags, unit and expected answer (required, isKnockout, expectedAnswer, currency/period) are set in the same call. A new field is required unless required is false. A knockout must be required and have a complete expected answer.

willingToRelocate is a yes/no question ("do you live in the job's area or are you willing to relocate there?"); once the form carries it, it replaces the automatic residence requirement derived from the position's location, and its expectedAnswer takes booleanValue. pretendedSalary collects an amount and takes currency and period together; its expectedAnswer uses operator/value or operator "between" with min and max. currentSalary also takes currency and period together, has no expected answer and cannot be a knockout.

The response reports criteriaVersionChanged: when true, the position's existing scores were computed against the previous form.

Inputs: jobDescriptionId (required), type, label, period, +7 more.

change_job_statusChange job position statusA
Destructive
Inspect

Change a job position status between open, paused, closed, and cancelled. Transitions to "open" trigger ATS integration side-effects (create job in the connected ATS, auto-sync candidates) when the organization has those integrations enabled.

Inputs: status (required), jobDescriptionId (required).

create_job_descriptionCreate job positionAInspect

Create a new job position. Automatically generates a default interview plan if none is provided, schedules embedding generation for AI matching, and optionally seeds a screening template. The job description and company description fields accept basic HTML (bold, italic, lists) and are sanitized server-side.

Inputs: title (required), locations (required), companyName (required), jobDescription (required), +7 more.

export_hiring_historyExport hiring historyAInspect

Export the organization's full hiring history to an Excel workbook, traceable from the opening of each vacancy to the hire. Three sheets joined by ID columns: vacancies (opening, first publication, closing and cancellation dates, status, opening reason, owners, target hires, number of applications and hires, days to first hire, and the job request it came from with its requester and approval date); applications (candidate, source, applied date, current stage, outcome, hire or rejection date and reason, score, days in process); stage movements (one row per stage change with its date, from/to stage, who moved it, rejection reason and days in the previous stage). Filters vacancies by opening date or by id. Up to 20000 applications per file; a larger history is exported in parts by narrowing the range. Dates are in UTC. The file is personal and can be downloaded for 24 hours.

Inputs: openedTo, openedFrom, jobDescriptionIds.

generate_job_draftDraft job position with AIA
Read-onlyIdempotent
Inspect

Generate an AI draft of a job posting from a short free-text brief (e.g. "Backend Engineer with 10 years of Node"). Nothing is created or saved. Each call runs an AI generation that takes several seconds and counts toward the organization's AI usage. Returns the drafted fields (title, description HTML, modality, salary, locations, benefits) plus the organization name and description. Optionally starts from an existing job position (baseJobDescriptionId).

Inputs: brief (required), baseJobDescriptionId.

get_application_form_answersGet application form answersA
Read-onlyIdempotent
Inspect

Get the answers a candidate submitted in the application form of one job position: each custom question with its label, type, whether it was required and the candidate's answer, plus the declared expected salary (declared.pretendedSalary) and location when present. When the position asked for salary as a free-text question, the amount is in answers, not in declared. Shows what the candidate actually wrote, independently of the matching score.

Inputs: candidateId (required), jobDescriptionId (required).

get_candidateGet candidate profileA
Read-onlyIdempotent
Inspect

Get the profile of a candidate by ID: the unified profile (merged from LinkedIn and resume data), contact data, notes, evaluations and the candidate's applications, each with the score the pipeline shows for that position (matchingScore). The expected salary is in pretendedSalary (amount, currency, period) when the candidate declared it or it was read from the resume; when it was asked as a free-text question it is in the application form answers instead. The current salary, when recorded, is in currentSalary. applicationsTruncated: true means older applications were left out. detail: "summary" (the default) returns the professional profile, contact data, notes, evaluations and applications; detail: "full" returns the whole stored record, including attachments. includeSources: true adds the raw linkedinData and resumeData structures (the raw resume text is never returned). includeResume: true adds a signed link to the resume PDF, valid for 1 hour, in resumeUrl.

Inputs: candidateId (required), detail, includeResume, includeSources.

get_candidate_score_breakdownExplain candidate scoreA
Read-onlyIdempotent
Inspect

Get why a candidate scored what they scored on one job position: the overall matching score with its per-criterion verdicts, knockout results, applied penalties and the position's full evaluation criteria, side by side. Use it whenever a recruiter questions or comments on a score — it is the only tool that shows which criterion produced which part of the number, and it tells you whether the score is still current or was computed against criteria that have since changed. When score.scoreModel is 'requirements' the client shows the requirements-based score: overall comes from score.requirementsScore (each requirement met with a grade of 8-10 from requirementsScore.version 'v6' on, 6-10 before — at most 8 when it is declared, i.e. backed only by the candidate's own word: their form answer or, when resolvedBy is 'interview', what they explicitly said in the AI interview about a vacancy criterion the profile had left 'a validar' (profileEvidence keeps the profile's own observation) —, partial (verdict 'partial', from 'v7' on: the candidate has it below a measurable threshold — at least half the years asked, or one language or study level below; for years and language levels code places it from the figures the model reports, and when code moved the model's verdict or counted the years itself the row's measured field holds the figures the verdict rests on (the evidence still quotes the model's own reading) —; it counts a fixed 4 with no grade, counts as covered and never caps a knockout), not met (0), or 'a validar' without evidence, which counts as a neutral 5 from requirementsScore.version 'v5' on — scores stored with 'v4' or earlier left it out of the average and graded form answers up to 10, so explain each score by its own version; plus up to 10 points of general analysis, blended 50/50 with interviewPerformance when there is an interview). From 'v6' a requirement weighs 2 when excluding (weight 'mustHave', which includes every knockout and every form question with an expected answer), 4 when an excluding one, knockouts included, the recruiter marked as weighing extra (extraWeight: true) and 1 when preferred, and a knockout not met — never one 'a validar' — caps the overall at 50, after the interview blend, as does a failed interview knockout question; knockoutFailed/knockoutReasons are its failed knockouts (any failed excluding requirement on 'v5' or earlier) plus the failed interview knockout questions, and breakdown, mustHaveEvaluations, the distance/residence penalties and profileMatchAudit stay at the top level of score but belong to the previous score, whose overall and knockout flag are in score.legacyScore — explain the number from requirementsScore, never from them. Every criterion reaches the score (usedForScreening is a legacy flag nothing reads); every criterion must be sent back with its isKnockout, extraWeight, visibleInCareerSite and usedForScreening flags exactly as returned here, because an update replaces the whole list.

Inputs: candidateId (required), jobDescriptionId (required).

get_candidates_with_scoresList position candidates with scoresA
Read-onlyIdempotent
Inspect

Get candidates for a specific job position with their matching scores included. Returns candidates sorted by score by default, avoiding N+1 queries. Paginate with cursor (from pageInfo.nextCursor); keep sortBy, sortOrder and minScore identical across pages, since the cursor is anchored to that ordering. If the previous page's last candidate leaves the result set mid-traversal (removed from the job, or rescored below minScore), the traversal still resumes from the position that candidate held.

Inputs: jobDescriptionId (required), limit, cursor, sortBy, +3 more.

get_dashboard_metricsGet recruitment metricsA
Read-onlyIdempotent
Inspect

Get recruitment metrics for the organization over a time window. Each metric states the unit it counts, and they are not directly comparable: candidatesCreatedInPeriod counts unique candidates created in the window, applicationsBySource counts applications (one candidate can submit several), and aiScreenedApplicationsByInterviewIntent is a subset of applications: only those submitted to screenings with the AI interview enabled. Each distribution includes totalApplications. meetings counts video-call interviews recorded by the Selenios notetaker, with a person interviewing the candidate; AI screening interviews are not part of it, and there is no count of AI interviews sent or completed.

Inputs: period.

get_job_descriptionGet job positionA
Read-onlyIdempotent
Inspect

Get the full details of a job position, including its evaluation criteria and technical requirements. Each criterion exposes its level and flags: "type" ("mustHave" or "niceToHave"), "isKnockout" (a mustHave that is a knockout: failing it caps the score at 50), "extraWeight" (a mustHave, knockouts included, that weighs double: x4 instead of x2), "visibleInCareerSite" (shown to candidates on the public career site) and "usedForScreening" (legacy, no longer used: every criterion is evaluated). Use this before editing criteria to inspect their current state.

Inputs: jobDescriptionId (required).

get_job_score_recalculation_stateCheck score recalculationA
Read-onlyIdempotent
Inspect

Check whether a bulk re-score of a job position can run right now. Returns canRecalculate; the reason when it cannot (a run already in progress, the one-per-hour cooldown, criteria unchanged since the last run, or no candidate with an outdated score); the minutes left on the cooldown; how many candidates would be re-scored; and the progress of a run in progress.

Inputs: jobDescriptionId (required).

get_meetingGet interviewA
Read-onlyIdempotent
Inspect

Get one interview as its screen shows it: title, status (pending = scheduled, active = in progress, completed, cancelled, archived, expired = scheduled time passed without a recording), date and time, type, candidate, job position, the interviewer's notes when the caller may see them, and whether a transcript and a report exist. Accepts the meeting meetingId, its _id, or a shared interview link (.../shared/).

Inputs: meetingId (required).

get_meeting_reportGet interview reportA
Read-onlyIdempotent
Inspect

Get the interview report of a meeting: the human-edited version when one exists, otherwise the AI-generated one. Accepts either the meeting meetingId or its _id.

Inputs: meetingId (required).

get_meeting_transcriptGet interview transcriptA
Read-onlyIdempotent
Inspect

Get the transcript of one interview: speaker-attributed entries with start and end times. Accepts either the meeting meetingId or its _id. For a finished interview it is the processed transcript; for an interview in progress, or one that ended minutes ago and is not processed yet, it is the real-time transcript captured so far, flagged live: true. Transcripts can be long.

Inputs: meetingId (required).

get_pipelineGet position pipelineA
Read-onlyIdempotent
Inspect

Get the recruitment pipeline stages for a specific job position.

Inputs: jobDescriptionId (required).

get_screening_configGet screening configurationA
Read-onlyIdempotent
Inspect

Get the screening configuration for a job position. Returns the public form schema, the interview questions (including expected answers and knockout flags), and AI interview settings.

Inputs: jobDescriptionId (required).

get_screening_interview_resultGet AI screening interview resultA
Read-onlyIdempotent
Inspect

Get the result of a candidate's AI screening interview for a job position: the interview transcript (speaker turns only) and the AI evaluation (overall score, interview performance, per-question evaluations, summary, pros and flags). Interviews held with a person are not included.

Inputs: candidateId (required), jobDescriptionId (required).

get_stage_timingGet pipeline stage timingA
Read-onlyIdempotent
Inspect

Get stage timing analytics for a job position, computed from every candidate's stage movement history: per stage, the average days from application to first reaching it, the average days spent in it (over candidates that already left it), and how many candidates sit in it right now. Use this for questions like "how long does a candidate take to reach/finish stage X" or "average days per stage".

Inputs: jobDescriptionId (required).

list_candidate_meetingsList candidate interviewsA
Read-onlyIdempotent
Inspect

List the interviews of one candidate: title, type, status, start time and job position, plus hasTranscript and hasReport flags. The transcript and the report themselves are not included. Paginated with cursor (from pageInfo.nextCursor) and incremental with updatedSince.

Inputs: candidateId (required), limit, cursor, sortBy, +3 more.

list_contact_templatesList email templatesA
Read-onlyIdempotent
Inspect

List the active email templates available to the organization for messaging candidates (its own and the global ones), without their body. Specialized system templates (scheduling) are not included. Each template has an id and a name that identify it when sending an email.

Inputs: stageType.

list_job_meetingsList position interviewsA
Read-onlyIdempotent
Inspect

List the interviews of a job position: title, candidate, type, status and start time, plus hasTranscript and hasReport flags. The transcript and the report themselves are not included. Paginated with cursor (from pageInfo.nextCursor) and incremental with updatedSince.

Inputs: jobDescriptionId (required), limit, cursor, sortBy, +3 more.

list_jobsList job positionsA
Read-onlyIdempotent
Inspect

List job positions/descriptions for the organization. Returns job title, department, location, status, and candidate counts. Paginate with cursor (from pageInfo.nextCursor) and sync incrementally with updatedSince.

Inputs: limit, cursor, sortBy, status, +2 more.

list_meetingsList interviews by dateA
Read-onlyIdempotent
Inspect

List the interviews and meetings scheduled in a date range, internal meetings included, optionally only those whose title contains given words (e.g. "the Check Point meeting on October 21", "which interviews did I have yesterday?"). Returns title, status, date and time, candidate, and whether a transcript and a report exist, oldest first. total counts every interview in the range; truncated: true means not all of them were returned and a narrower range or title returns the rest. It does not search what was said in the interviews.

Inputs: to (required), from (required), title.

list_rejection_reasonsList rejection reasonsA
Read-onlyIdempotent
Inspect

List the rejection reasons configured for the organization, grouped by category. Use a value from this list as rejectionReason when rejecting a candidate.

Inputs: no named parameters.

list_unread_messagesList unread candidate repliesA
Read-onlyIdempotent
Inspect

List the unread email replies from candidates, grouped by candidate (most recent first), with the unread count, the latest subject and a preview. Covers the whole account or one job position. Only email replies have a read state; WhatsApp messages are not included. The response carries asOf, the moment the list was taken.

Inputs: limit, offset, jobDescriptionId.

mark_messages_readMark candidate replies as readA
DestructiveIdempotent
Inspect

Mark candidate email replies as read: for specific candidates (candidateIds, no position needed), for one job position, or for the whole account (only the candidates this user can see). receivedBefore limits it to the replies received up to that moment, so later replies stay unread.

Inputs: candidateIds, receivedBefore, jobDescriptionId.

match_candidate_to_jobRecalculate candidate scoreA
Destructive
Inspect

Recalculate the AI matching score for a candidate against a specific job position. Requires that the job has a screening configured and an application linking the candidate to the job. Returns the newly computed score.

Inputs: candidateId (required), jobDescriptionId (required).

move_candidate_stageMove candidate to stageA
Destructive
Inspect

Move a candidate to another stage of a job position pipeline, with the same rules as the interface (restricted stages, onboarding document gate on hire, multi-location ownership, integrations). Moving to the Rejected stage takes a rejection reason and category.

Inputs: stageId (required), candidateId (required), jobDescriptionId (required), locationId, +2 more.

move_pipeline_stagesReorder pipeline stagesA
DestructiveIdempotent
Inspect

Reorder the pipeline of a job position: move one or more existing stages, together and in the given order, right after another stage — or to the start of the plan when afterStage is omitted. Same as dragging them in the position screen: any stage can move, and nothing else about them changes (name, candidates, stage agents).

Inputs: stages (required), jobDescriptionId (required), afterStage.

recalculate_job_scoresRecalculate position scoresA
Destructive
Inspect

Re-score the candidates of a job position against its current evaluation criteria. Until it runs after a criteria change, every score in that position's pipeline reflects the previous criteria. The run is asynchronous and limited to one per position per hour. It is refused while another run is in progress, during the cooldown, when the criteria have not changed since the last run, or when no candidate has an outdated score; the refusal states which.

Inputs: jobDescriptionId (required).

reject_candidateReject candidateA
Destructive
Inspect

Reject a candidate for a job position: moves them to the Rejected stage and records why. Takes a rejectionReason (a value from the organization's catalog of rejection reasons) and a rejectionCategory. Runs the same rules and integrations as rejecting from the interface.

Inputs: candidateId (required), rejectionReason (required), jobDescriptionId (required), rejectionCategory (required), +1 more.

remove_candidate_tagsRemove candidate tagsB
DestructiveIdempotent
Inspect

Remove one or more tags from a candidate. Tag matching is case-insensitive.

Inputs: tags (required), candidateId (required).

remove_screening_form_fieldRemove application form fieldA
DestructiveIdempotent
Inspect

Remove one field from the application form of a job position. Candidates are no longer asked it. Answers already submitted are kept on their applications but are no longer shown on the form or evaluated. fieldName is the key in configuration.formSchema.properties of the position's screening configuration, and fieldLabel is that property's title, verbatim; a label that does not match is rejected. The base fields firstName, lastName and email cannot be removed. On a professional application, linkedinUrl or resumeFile must stay required: removing the only required one of the two is rejected. The response reports criteriaVersionChanged: when true, the removed field was part of what candidates were scored against.

Inputs: fieldName (required), fieldLabel (required), jobDescriptionId (required).

reorder_screening_form_fieldsReorder application form fieldsA
DestructiveIdempotent
Inspect

Set the order in which the candidate sees the fields of a job position's application form. fieldNames lists every field key of the form (configuration.formSchema.properties) exactly once, in the new order: the whole order, not only the fields that moved. A list that omits a field, repeats one or names one the form does not have is rejected, and the error says which. It changes presentation only, not scoring.

Inputs: fieldNames (required), jobDescriptionId (required).

search_candidatesSearch candidatesA
Read-onlyIdempotent
Inspect

Search and filter candidates across all job positions. Supports text search by name, skills or experience; direct search by email address, LinkedIn URL or candidate name; and semantic natural-language queries such as "candidates with React experience in Buenos Aires". Can filter by job position and by pipeline stage ID. The response shape depends on the path: filter-only queries (no query) include totalMatching, filterOptions and appliedFilters; text and semantic queries return candidates, searchType and returnedCount, with no global match count. Paginated with cursor (from pageInfo.nextCursor) and incremental with updatedSince; semantic results are ranked by relevance and report pageInfo.cursorSupported: false.

Inputs: tags, limit, query, stage, +6 more.

search_meeting_transcriptsSearch interview transcriptsA
Read-onlyIdempotent
Inspect

Search what was said in interviews: returns the interviews whose transcript or title contains any of the given words or phrases, with the matching excerpts (speaker and second); titleMatch is true when the title matched. Examples: "who mentioned Kubernetes?", "in which interview did they talk about salary?". The match is literal, case- and accent-insensitive, not semantic. Interviews are transcribed in the language they were held in, so one call accepts up to 12 terms: synonyms and translations together (e.g. "salary", "compensation", "salario", "sueldo", "salário"). A term with several words matches an entry that says all of them, in any order. Can be narrowed by job position, candidate or date range. It reads the 300 most recently added interviews that match the filters, and scanLimitReached: true means older interviews were not searched. Only processed transcripts are searched, not interviews in progress. The results contain only the interviews that matched, not every interview of a period.

Inputs: terms (required), to, from, limit, +2 more.

send_candidate_emailSend email to candidateA
Destructive
Inspect

Send an email to a candidate from the organization's configured email address. Takes either a free-form subject and body, or an email template (by templateId or templateName) whose {{variables}} are filled in for the candidate and job position. The email reaches the candidate.

Inputs: candidateId (required), body, subject, templateId, +2 more.

set_job_closing_dateCorrect job position closing dateA
DestructiveIdempotent
Inspect

Correct the closing date of a job position that is already closed, like the pencil next to the closing date on the position screen. It does not close a position: an open, paused or cancelled position is refused, and so is a date later than today. Closing always happens as of now; a position that has to end up closed on an earlier date is closed first and its date corrected afterwards. Saving the date regenerates the closing report of the position.

Inputs: closedAt (required), jobDescriptionId (required).

set_job_multipostPublish job position on job boardsA
DestructiveIdempotent
Inspect

Enable or disable multiposting for a job position. When enabled, the job is included in the external XML job feed (VONQ / LinkedIn) and published on those channels. Only open, non-confidential jobs with a resolvable location (or a company headquarters location) can be enabled. Requires an administrator role. Paid LinkedIn Job Slots are managed elsewhere.

Inputs: enabled (required), jobDescriptionId (required).

update_career_site_settingsUpdate career site settingsA
DestructiveIdempotent
Inspect

Update the organization's public career site settings. Currently supports showing or hiding the salary range on published job posts.

Inputs: showSalaryRange.

update_job_descriptionUpdate job positionA
DestructiveIdempotent
Inspect

Update an existing job position. Only the fields passed are modified. Arrays such as evaluationCriteria and technicalRequirements replace the existing list entirely: a criterion left out is deleted, and each criterion keeps its isKnockout, extraWeight, visibleInCareerSite and usedForScreening flags only if they are sent again (a criterion sent without them loses its knockout or extra weight and is published on the public career site). Changing the criteria does not re-score candidates: existing scores reflect the previous criteria until a recalculation runs. HTML fields are sanitized server-side. The open/paused/closed/cancelled status is not changed here.

Inputs: jobDescriptionId (required), title, videoUrl, locations, +10 more.

update_screening_form_fieldUpdate application form fieldA
DestructiveIdempotent
Inspect

Change one existing field of the application form of a job position: whether it is required, whether an answer outside the expected one disqualifies the candidate (knockout), its expected answer (expectedAnswer), the unit of an amount field (currency + period, both or neither) and, on the address field "neighborhoodLocation" only, the maximum commute distance in kilometres. fieldName is the key in configuration.formSchema.properties of the position's screening configuration, and fieldLabel is that property's title, verbatim; a label that does not match is rejected. A knockout must be a required field with a complete expected answer (on the address field, maxDistanceKm). The base fields firstName, lastName and email are always required. On a professional application, linkedinUrl or resumeFile must stay required: making the only required one of the two optional is rejected. The response reports criteriaVersionChanged: when true, the position's existing scores were computed against the previous form.

Inputs: fieldName (required), fieldLabel (required), jobDescriptionId (required), period, +6 more.

update_screening_questionsReplace screening questionsA
DestructiveIdempotent
Inspect

Replace the full list of interview questions for the screening of a job position. Each question requires a non-empty prompt, a non-empty expected answer, and a knockout flag. Maximum 15 questions. When the screening has a live AI agent, the evaluation criteria are resynced so the scorer uses the new questions.

Inputs: questions (required), jobDescriptionId (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      11 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources