_ registry / mcp + a2a http-sse · checked 58m ago

ssrs2

https://ssrs2.net

Registry code: 330df80cacc974cd

api record

SSRS2 checks, renders and converts report definitions (RDL and RDLC, the report format of SQL Server Reporting Services and Report Viewer) and Markdown with the Report Viewer engine.

A REPORT (.rdlc, .rdl): look at its outline first (describe_report: each item's role, place and size). After writing or changing one, call validate_report with its XML as rdlc: each problem comes back with a code, the item, the property, the expression and a hint. Fix the errors and call it again until ok is true, then call render_preview to look at the pages. Reports render with made-up rows unless you pass real…

endpoint
https://ssrs2.net/mcp
door code
7df896acf17ee899
protocol
http-sse ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is ssrs2 live?
Yes — it answered the hub's last check (checked 58m ago). It answered 100% of checks over the last 30 days.
Is ssrs2 free to use?
Not measured yet.
What tools does ssrs2 have?
6 tools: edit_report, compare_reports, describe_report, convert_report, render_preview, validate_report.
Is ssrs2 safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
139ms

last good check

priced tools
0

of 6 tools

_ answered our checks, 90 days 2 checks · signed record
  • unknown → live
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
1

through this hub

calls served
1

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 6 tools
6 never probed 0 of 6 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • edit_report unknown never probed

    Changes a report definition (RDL, RDLC) given as its XML by operations (the SSRS2 designer's own), all or none. The text is patched (the rest as it was), then checked: its new problems and pages said. The answer's rdlc is the changed report (past 200 KB, url and curl: a download within ten minutes). Operations ("op"): dataset, parameter, page, header, footer, code, textbox, table, matrix, list, chart, gauge, indicator, databar, sparkline, image, barcode, subreport, line, rectangle, set, remove, space, move, swap, copy, field, column, remove_column, row, total, group, sort, widths, filter. A new item goes "after" or "before" an item or a role (role:signature), "in" a container or "at":[x, y] cm. Call help: ["textbox","set"] first: their words.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "fit": {
      "type": "boolean",
      "default": false,
      "description": "With keepPages: a block that costs rows is written in the form checked to keep them."
    },
    "help": {
      "description": "Operations' names, or true."
    },
    "rdlc": {
      "type": [
        "string",
        "null"
      ],
      "description": "The report's XML."
    },
    "check": {
      "type": "boolean",
      "default": true,
      "description": "Check after (default true)."
    },
    "edits": {
      "description": "Or exact replacements: [{find, replace, in?, all?}]."
    },
    "detail": {
      "type": [
        "string",
        "null"
      ],
      "description": "\"full\": every item, the diff whole."
    },
    "dryRun": {
      "type": "boolean",
      "default": false,
      "description": "The diff, not the report."
    },
    "rewrite": {
      "type": "boolean",
      "default": false,
      "description": "Write anew a report that cannot be patched."
    },
    "summary": {
      "type": [
        "string",
        "null"
      ],
      "description": "Said back."
    },
    "maxPages": {
      "type": [
        "integer",
        "null"
      ],
      "description": "Refuse a report printing more pages."
    },
    "pictures": {
      "type": [
        "object",
        "null"
      ],
      "description": "Pictures an image names by its file: {\"path\": \"<base64>\"}.",
      "additionalProperties": {
        "type": [
          "string",
          "null"
        ]
      }
    },
    "variants": {
      "description": "As validate_report's; their pages said."
    },
    "keepPages": {
      "type": "boolean",
      "default": false,
      "description": "Refuse a change that would print more pages, or at fewer table rows (variants, rowCounts too)."
    },
    "rowCounts": {
      "description": "As validate_report's: {DataSet: \"1..30\"}."
    },
    "operations": {
      "type": [
        "array",
        "null"
      ],
      "items": {},
      "description": "The operations, in order."
    },
    "parameters": {
      "type": [
        "object",
        "null"
      ],
      "description": "Parameter values.",
      "additionalProperties": {
        "type": [
          "string",
          "null"
        ]
      }
    },
    "sampleData": {
      "description": "Rows: {DataSet: [{Field: value}]}."
    },
    "baseVersion": {
      "type": [
        "string",
        "null"
      ],
      "description": "describe_report's version."
    }
  }
}
    arguments 114 lines
  • compare_reports unknown never probed

    Groups report definitions (RDL or RDLC) by structure, to plan one change across many: a group's reports have the same items, datasets, parameters and code modules and differ only in places, texts and looks, so one set of operations naming their items changes them alike. Returns groups, the largest first: structure (edit_report's structure), roles (what role:signature and the like name there), differs (how its first report differs from the first group's), places (items placed otherwise), and versions: each report and its version.

    mcp-tool

    {
  "type": "object",
  "required": [
    "reports"
  ],
  "properties": {
    "detail": {
      "type": [
        "string",
        "null"
      ],
      "description": "\"full\": each group's reports listed too, beside their versions."
    },
    "reports": {
      "type": "object",
      "description": "The reports by name: {\"Receipt_de-CH.rdlc\": \"<the report's XML>\", ...}; 50 at most, 20 MB in all.",
      "additionalProperties": {
        "type": "string"
      }
    }
  }
}
    arguments 22 lines
  • describe_report unknown never probed

    Outlines a report definition (RDL or RDLC) to plan a change: its page, datasets and fields, parameters, and every item top to bottom with its kind, place and size in cm, what it shows and does (hidden, toggled, page breaks), and its role (title, table, totals, declaration, signature...), which role:signature and the like name in edit_report and validate_report whatever the report calls the item. Returns version (edit_report's baseVersion) and outline; with item, that part's XML as written, with its lines (to copy an edit's find from).

    mcp-tool

    {
  "type": "object",
  "required": [
    "rdlc"
  ],
  "properties": {
    "item": {
      "type": [
        "string",
        "null"
      ],
      "description": "One part in full: a name, a role (role:signature) or a path (WorkInstructions/TablixRow[3]): its outline and XML."
    },
    "rdlc": {
      "type": "string",
      "description": "The report definition's XML (RDL or RDLC)."
    },
    "detail": {
      "type": [
        "string",
        "null"
      ],
      "description": "\"full\": every text whole and why each role was guessed."
    }
  }
}
    arguments 26 lines
  • convert_report unknown 58m ago

    Converts a report (RDL or RDLC) or Markdown (a document, or slides) with SSRS2, the Report Viewer engine, to pptx (PowerPoint's own text boxes, tables and pictures, a slide per page: a Markdown deck becomes a deck), pdf, docx, xlsx, mhtml, tiff, png (the first page), csv or xml. It is checked first, as validate_report checks it: with errors nothing is written. Returns validate_report's answer and written: the file's name and size, url (downloaded once, within ten minutes), curl (the command that saves it), and what it holds read back as PowerPoint (slides) or Word and a PDF reader (document) get it. help: ["answers"] says more.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "help": {
      "description": "true, or topics ([\"markdown\", \"decks\"]): the reference only."
    },
    "name": {
      "type": [
        "string",
        "null"
      ],
      "description": "The file's name, without its extension (default: the Markdown's title, else report)."
    },
    "rdlc": {
      "type": [
        "string",
        "null"
      ],
      "description": "The report definition's XML (RDL or RDLC). Give rdlc or markdown."
    },
    "format": {
      "type": [
        "string",
        "null"
      ],
      "description": "pptx (default), pdf, docx, xlsx, mhtml, tiff, png, csv or xml."
    },
    "culture": {
      "type": [
        "string",
        "null"
      ],
      "description": "The culture of a report that names no Language (en-US, de-CH); left out, en-US."
    },
    "markdown": {
      "type": [
        "string",
        "null"
      ],
      "description": "Markdown's text: a document, or slides with marp: true. Give rdlc or markdown."
    },
    "pictures": {
      "type": [
        "object",
        "null"
      ],
      "description": "The pictures the Markdown names, by its paths: {\"images/chart.png\": \"<base64>\"}; 5 MB each, 20 MB in all.",
      "additionalProperties": {
        "type": [
          "string",
          "null"
        ]
      }
    },
    "parameters": {
      "type": [
        "object",
        "null"
      ],
      "description": "Report parameter values by name (a multi-value one's separated by commas).",
      "additionalProperties": {
        "type": [
          "string",
          "null"
        ]
      }
    },
    "sampleData": {
      "description": "Rows per dataset: {\"DataSet\": [{\"Field\": value}]}, dates as ISO text. Left out, made up from the fields' types."
    }
  }
}
    arguments 72 lines
  • render_preview unknown 58m ago

    Renders a report definition (RDL or RDLC) or Markdown (a document, or slides: a page each) with SSRS2, the Report Viewer engine, and returns its pages as PNG, as a PDF of it would show them: a JSON summary first (what validate_report answers, no need to validate first; madeUpRows; conversion for Markdown, what it approximated at its lines; text, what the pages print, page by page in reading order, where values are read exactly), then an image per page, or one image of numbered thumbnails (sheet) to see a deck or a long report whole. A report with errors is not rendered. help: ["answers"] says more.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "dpi": {
      "type": "integer",
      "default": 96,
      "description": "The images' dots per inch, 48 to 200 (default 96: an A4 page is 794 x 1123 pixels)."
    },
    "help": {
      "description": "true, or topics ([\"markdown\", \"decks\"]): the reference only."
    },
    "rdlc": {
      "type": [
        "string",
        "null"
      ],
      "description": "The report definition's XML (RDL or RDLC). Give rdlc or markdown."
    },
    "pages": {
      "type": [
        "integer",
        "null"
      ],
      "description": "Pages to return: 3 by default, 10 at most; with sheet, 30."
    },
    "sheet": {
      "type": "boolean",
      "default": false,
      "description": "One image of up to 30 pages as numbered thumbnails, too small to read: look at a page itself for that."
    },
    "culture": {
      "type": [
        "string",
        "null"
      ],
      "description": "The culture of a report that names no Language (en-US, de-CH); left out, en-US."
    },
    "markdown": {
      "type": [
        "string",
        "null"
      ],
      "description": "Markdown's text: a document, or slides with marp: true. Give rdlc or markdown."
    },
    "pictures": {
      "type": [
        "object",
        "null"
      ],
      "description": "The pictures the Markdown names, by its paths: {\"images/chart.png\": \"<base64>\"}; 5 MB each, 20 MB in all.",
      "additionalProperties": {
        "type": [
          "string",
          "null"
        ]
      }
    },
    "firstPage": {
      "type": "integer",
      "default": 1,
      "description": "The first page to return (default 1)."
    },
    "madeUpRows": {
      "description": "\"all\": every made-up row in the answer, not a summary."
    },
    "parameters": {
      "type": [
        "object",
        "null"
      ],
      "description": "Report parameter values by name (a multi-value one's separated by commas).",
      "additionalProperties": {
        "type": [
          "string",
          "null"
        ]
      }
    },
    "sampleData": {
      "description": "Rows per dataset: {\"DataSet\": [{\"Field\": value}]}, dates as ISO text. Left out, made up from the fields' types."
    }
  }
}
    arguments 83 lines
  • validate_report unknown 58m ago

    Checks a report definition (RDL or RDLC) or Markdown with the Report Viewer engine: XML, schema, every expression compiled, then a run with rows through every page. Returns ok, a summary and diagnostics (code, severity, item, property, expression, line, message, hint); atRunTime counts what failed as it ran (#Error cells). Call it after each change until ok is true and atRunTime absent. Expressions are Visual Basic and may only compute (restrictedCode). Also layout, expect, variants, rowCounts and the report as it was (baselineRdlc): help: ["checks"].

    mcp-tool

    {
  "type": "object",
  "properties": {
    "help": {
      "description": "true, or topics ([\"markdown\", \"decks\"]): the reference only."
    },
    "rdlc": {
      "type": [
        "string",
        "null"
      ],
      "description": "The report definition's XML (RDL or RDLC). Give rdlc or markdown."
    },
    "expect": {
      "description": "Rules: {\"order\": [\"role:table\", \"Block?\", \"role:signature\"]}, samePage, page, pages, maxPages, noOverlap. An item named and not printed fails its rule, unless written Name? (a variant may hide it)."
    },
    "layout": {
      "description": "true, or names and roles (role:signature): where each item printed, its page and place in cm."
    },
    "render": {
      "type": "boolean",
      "default": true,
      "description": "false: the definition only, no expression runs."
    },
    "culture": {
      "type": [
        "string",
        "null"
      ],
      "description": "The culture of a report that names no Language (en-US, de-CH); left out, en-US."
    },
    "markdown": {
      "type": [
        "string",
        "null"
      ],
      "description": "Markdown's text: a document, or slides with marp: true. Give rdlc or markdown."
    },
    "pictures": {
      "type": [
        "object",
        "null"
      ],
      "description": "The pictures the Markdown names, by its paths: {\"images/chart.png\": \"<base64>\"}; 5 MB each, 20 MB in all.",
      "additionalProperties": {
        "type": [
          "string",
          "null"
        ]
      }
    },
    "variants": {
      "description": "Renders again with rows changed: [{\"name\": \"no deposit\", \"sampleData\": {\"Deposit\": null}}]."
    },
    "rowCounts": {
      "description": "{\"Requests\": \"1..30\"}: the pages of each count and the first that adds a page."
    },
    "madeUpRows": {
      "description": "\"all\": every made-up row in the answer, not a summary."
    },
    "parameters": {
      "type": [
        "object",
        "null"
      ],
      "description": "Report parameter values by name (a multi-value one's separated by commas).",
      "additionalProperties": {
        "type": [
          "string",
          "null"
        ]
      }
    },
    "sampleData": {
      "description": "Rows per dataset: {\"DataSet\": [{\"Field\": value}]}, dates as ISO text. Left out, made up from the fields' types."
    },
    "baselineRdlc": {
      "type": [
        "string",
        "null"
      ],
      "description": "The report as it was (its XML): only new warnings are said, with pages before."
    }
  }
}
    arguments 85 lines
_ try it over mcp through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 330df80cacc974cd.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/330df80cacc974cd/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/330df80cacc974cd/badge.svg)](https://brick.blue/agent/330df80cacc974cd?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we knowoff the mcp door
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
1
ok
1
failed
0
success rate
100%
median latency
1,286ms
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

1 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.